{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "77b8f875", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:38:08.084437Z", "iopub.status.busy": "2024-05-14T14:38:08.084099Z", "iopub.status.idle": "2024-05-14T14:39:09.090683Z", "shell.execute_reply": "2024-05-14T14:39:09.089627Z" }, "papermill": { "duration": 61.014156, "end_time": "2024-05-14T14:39:09.093219", "exception": false, "start_time": "2024-05-14T14:38:08.079063", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "%%capture\n", "!pip install stable-baselines3[extra]\n", "!pip install moviepy" ] }, { "cell_type": "code", "execution_count": 2, "id": "f547942b", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:09.102103Z", "iopub.status.busy": "2024-05-14T14:39:09.101786Z", "iopub.status.idle": "2024-05-14T14:39:25.987681Z", "shell.execute_reply": "2024-05-14T14:39:25.986695Z" }, "papermill": { "duration": 16.892884, "end_time": "2024-05-14T14:39:25.990128", "exception": false, "start_time": "2024-05-14T14:39:09.097244", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2024-05-14 14:39:16.039893: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", "2024-05-14 14:39:16.039990: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", "2024-05-14 14:39:16.182583: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n" ] } ], "source": [ "from stable_baselines3 import A2C\n", "from stable_baselines3.common.monitor import Monitor\n", "from stable_baselines3.common.callbacks import BaseCallback, EvalCallback, CallbackList\n", "from stable_baselines3.common.logger import Video, HParam, TensorBoardOutputFormat\n", "from stable_baselines3.common.evaluation import evaluate_policy\n", "\n", "from typing import Any, Dict\n", "\n", "import gymnasium as gym\n", "import torch as th\n", "import numpy as np\n", "\n", "# =====File names=====\n", "MODEL_FILE_NAME = \"ALE-Pacman-v5\"\n", "POLICY_FILE_NAME = \"a2c_policy_pacman_v2\"\n", "\n", "# =====Model Config=====\n", "# Evaluate in 20ths\n", "EVAL_CALLBACK_FREQ = 75_000\n", "# Record in quarters (the last one won't record, will have to do manually)\n", "VIDEO_CALLBACK_FREQ = 375_000\n", "FRAMESKIP = 4\n", "NUM_TIMESTEPS = 1_500_000\n", "\n", "# =====Hyperparams=====\n", "# The hyperparams should be defined here, however I want to run this just defaults for this run" ] }, { "cell_type": "code", "execution_count": 3, "id": "667f65d4", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:25.999620Z", "iopub.status.busy": "2024-05-14T14:39:25.998467Z", "iopub.status.idle": "2024-05-14T14:39:26.009249Z", "shell.execute_reply": "2024-05-14T14:39:26.008540Z" }, "jupyter": { "source_hidden": true }, "papermill": { "duration": 0.017201, "end_time": "2024-05-14T14:39:26.011150", "exception": false, "start_time": "2024-05-14T14:39:25.993949", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# VideoRecorderCallback\n", "# The VideoRecorderCallback should record a video of the agent in the evaluation environment\n", "# every render_freq timesteps. It will record one episode. It will also record one episode when\n", "# the training has been completed\n", "\n", "class VideoRecorderCallback(BaseCallback):\n", " def __init__(self, eval_env: gym.Env, render_freq: int, n_eval_episodes: int = 1, deterministic: bool = True):\n", " \"\"\"\n", " Records a video of an agent's trajectory traversing ``eval_env`` and logs it to TensorBoard.\n", " :param eval_env: A gym environment from which the trajectory is recorded\n", " :param render_freq: Render the agent's trajectory every eval_freq call of the callback.\n", " :param n_eval_episodes: Number of episodes to render\n", " :param deterministic: Whether to use deterministic or stochastic policy\n", " \"\"\"\n", " super().__init__()\n", " self._eval_env = eval_env\n", " self._render_freq = render_freq\n", " self._n_eval_episodes = n_eval_episodes\n", " self._deterministic = deterministic\n", "\n", " def _on_step(self) -> bool:\n", " if self.n_calls % self._render_freq == 0:\n", " screens = []\n", "\n", " def grab_screens(_locals: Dict[str, Any], _globals: Dict[str, Any]) -> None:\n", " \"\"\"\n", " Renders the environment in its current state, recording the screen in the captured `screens` list\n", " :param _locals: A dictionary containing all local variables of the callback's scope\n", " :param _globals: A dictionary containing all global variables of the callback's scope\n", " \"\"\"\n", " screen = self._eval_env.render()\n", " # PyTorch uses CxHxW vs HxWxC gym (and tensorflow) image convention\n", " screens.append(screen.transpose(2, 0, 1))\n", "\n", " evaluate_policy(\n", " self.model,\n", " self._eval_env,\n", " callback=grab_screens,\n", " n_eval_episodes=self._n_eval_episodes,\n", " deterministic=self._deterministic,\n", " )\n", " self.logger.record(\n", " \"trajectory/video\",\n", " Video(th.from_numpy(np.array([screens])), fps=60),\n", " exclude=(\"stdout\", \"log\", \"json\", \"csv\"),\n", " )\n", " return True" ] }, { "cell_type": "code", "execution_count": 4, "id": "87b4aed5", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:26.018930Z", "iopub.status.busy": "2024-05-14T14:39:26.018683Z", "iopub.status.idle": "2024-05-14T14:39:26.028115Z", "shell.execute_reply": "2024-05-14T14:39:26.027214Z" }, "papermill": { "duration": 0.015461, "end_time": "2024-05-14T14:39:26.029962", "exception": false, "start_time": "2024-05-14T14:39:26.014501", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# HParamCallback\n", "# This should log the hyperparameters specified and map the metrics that are logged to \n", "# the appropriate run.\n", "class HParamCallback(BaseCallback):\n", " \"\"\"\n", " Saves the hyperparameters and metrics at the start of the training, and logs them to TensorBoard.\n", " \"\"\" \n", " def __init__(self):\n", " super().__init__()\n", " \n", "\n", " def _on_training_start(self) -> None:\n", " \n", " hparam_dict = {\n", " \"algorithm\": self.model.__class__.__name__,\n", " \"policy\": self.model.policy.__class__.__name__,\n", " \"environment\": self.model.env.__class__.__name__,\n", " \"learning_rate\": self.model.learning_rate,\n", " \"n_steps\": self.model.n_steps,\n", " \"gamma\": self.model.gamma,\n", " \"gae_lambda\": self.model.gae_lambda,\n", " \"ent_coef\": self.model.ent_coef,\n", " \"vf_coef\": self.model.vf_coef,\n", " \"max_grad_norm\": self.model.max_grad_norm,\n", "# \"rms_prop_eps\": self.model.rms_prop_eps, Threw error, model has no attribute\n", "# \"use_rms_prop\": self.model.use_rms_prop, Threw error, model has no attribute\n", " \"use_sde\": self.model.use_sde,\n", " \"sde_sample_freq\": self.model.sde_sample_freq\n", " }\n", " # define the metrics that will appear in the `HPARAMS` Tensorboard tab by referencing their tag\n", " # Tensorbaord will find & display metrics from the `SCALARS` tab\n", " metric_dict = {\n", " \"eval/mean_ep_length\": 0,\n", " \"eval/mean_reward\": 0,\n", " \"rollout/ep_len_mean\": 0,\n", " \"rollout/ep_rew_mean\": 0,\n", " \"rollout/exploration_rate\": 0,\n", " \"time/_episode_num\": 0,\n", " \"time/fps\": 0,\n", " \"time/total_timesteps\": 0,\n", " \"train/learning_rate\": 0.0,\n", " \"train/loss\": 0.0,\n", " \"train/n_updates\": 0.0,\n", " \"locals/rewards\": 0.0,\n", " \"locals/infos_0_lives\": 0.0,\n", " \"locals/num_collected_steps\": 0.0,\n", " \"locals/num_collected_episodes\": 0.0\n", " }\n", " \n", " self.logger.record(\n", " \"hparams\",\n", " HParam(hparam_dict, metric_dict),\n", " exclude=(\"stdout\", \"log\", \"json\", \"csv\"),\n", " )\n", " \n", " def _on_step(self) -> bool:\n", " return True" ] }, { "cell_type": "code", "execution_count": 5, "id": "9ed2f5a4", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:26.037879Z", "iopub.status.busy": "2024-05-14T14:39:26.037621Z", "iopub.status.idle": "2024-05-14T14:39:26.050066Z", "shell.execute_reply": "2024-05-14T14:39:26.049310Z" }, "papermill": { "duration": 0.018541, "end_time": "2024-05-14T14:39:26.052089", "exception": false, "start_time": "2024-05-14T14:39:26.033548", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# PlotTensorboardValuesCallback\n", "# This callback should log values to tensorboard on every step. \n", "# The self.logger class should plot a new scalar value when recording.\n", "\n", "class PlotTensorboardValuesCallback(BaseCallback):\n", " \"\"\"\n", " Custom callback for plotting additional values in tensorboard.\n", " \"\"\"\n", " def __init__(self, eval_env: gym.Env, train_env: gym.Env, model: A2C, verbose=0):\n", " super().__init__(verbose)\n", " self._eval_env = eval_env\n", " self._train_env = train_env\n", " self._model = model\n", "\n", " def _on_training_start(self) -> None:\n", " output_formats = self.logger.output_formats\n", " # Save reference to tensorboard formatter object\n", " # note: the failure case (not formatter found) is not handled here, should be done with try/except.\n", " try:\n", " self.tb_formatter = next(formatter for formatter in output_formats if isinstance(formatter, TensorBoardOutputFormat))\n", " except:\n", " print(\"Exception thrown in tb_formatter initialization.\") \n", " \n", " self.tb_formatter.writer.add_text(\"metadata/eval_env\", str(self._eval_env.metadata), self.num_timesteps)\n", " self.tb_formatter.writer.flush()\n", " self.tb_formatter.writer.add_text(\"metadata/train_env\", str(self._train_env.metadata), self.num_timesteps)\n", " self.tb_formatter.writer.flush()\n", " \n", "\n", " def _on_step(self) -> bool:\n", " self.logger.record(\"time/_episode_num\", self.model._episode_num, exclude=(\"stdout\", \"log\", \"json\", \"csv\"))\n", " self.logger.record(\"train/n_updates\", self.model._n_updates, exclude=(\"stdout\", \"log\", \"json\", \"csv\"))\n", " self.logger.record(\"locals/rewards\", self.locals[\"rewards\"], exclude=(\"stdout\", \"log\", \"json\", \"csv\"))\n", " self.logger.record(\"locals/infos_0_lives\", self.locals[\"infos\"][0][\"lives\"], exclude=(\"stdout\", \"log\", \"json\", \"csv\"))\n", " \n", " return True\n", " \n", " def _on_training_end(self) -> None:\n", " self.tb_formatter.writer.add_text(\"metadata/eval_env\", str(self._eval_env.metadata), self.num_timesteps)\n", " self.tb_formatter.writer.flush()\n", " self.tb_formatter.writer.add_text(\"metadata/train_env\", str(self._train_env.metadata), self.num_timesteps)\n", " self.tb_formatter.writer.flush()" ] }, { "cell_type": "code", "execution_count": 6, "id": "525312a1", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:26.059687Z", "iopub.status.busy": "2024-05-14T14:39:26.059443Z", "iopub.status.idle": "2024-05-14T14:39:28.963281Z", "shell.execute_reply": "2024-05-14T14:39:28.962460Z" }, "papermill": { "duration": 2.910274, "end_time": "2024-05-14T14:39:28.965712", "exception": false, "start_time": "2024-05-14T14:39:26.055438", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "A.L.E: Arcade Learning Environment (version 0.8.1+53f58b7)\n", "[Powered by Stella]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Using cuda device\n", "Wrapping the env with a `Monitor` wrapper\n", "Wrapping the env in a DummyVecEnv.\n", "Wrapping the env in a VecTransposeImage.\n" ] } ], "source": [ "# make the training and evaluation environments\n", "eval_env = Monitor(gym.make(\"ALE/Pacman-v5\", render_mode=\"rgb_array\", frameskip=FRAMESKIP))\n", "train_env = gym.make(\"ALE/Pacman-v5\", render_mode=\"rgb_array\", frameskip=FRAMESKIP)\n", "\n", "# Make the model with specified hyperparams\n", "model = A2C(\n", " \"CnnPolicy\",\n", " train_env,\n", " verbose=1,\n", " tensorboard_log=\"./\",\n", " )" ] }, { "cell_type": "code", "execution_count": 7, "id": "c7362bec", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:28.980070Z", "iopub.status.busy": "2024-05-14T14:39:28.979758Z", "iopub.status.idle": "2024-05-14T14:39:28.986106Z", "shell.execute_reply": "2024-05-14T14:39:28.985240Z" }, "papermill": { "duration": 0.013086, "end_time": "2024-05-14T14:39:28.988025", "exception": false, "start_time": "2024-05-14T14:39:28.974939", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# Define the callbacks and put them in a list\n", "eval_callback = EvalCallback(\n", " eval_env,\n", " best_model_save_path=\"./best_model/\",\n", " log_path=\"./evals/\",\n", " eval_freq=EVAL_CALLBACK_FREQ,\n", " n_eval_episodes=10,\n", " deterministic=True,\n", " render=False)\n", "\n", "tbplot_callback = PlotTensorboardValuesCallback(eval_env=eval_env, train_env=train_env, model=model)\n", "video_callback = VideoRecorderCallback(eval_env, render_freq=VIDEO_CALLBACK_FREQ)\n", "hparam_callback = HParamCallback()\n", "\n", "callback_list = CallbackList([hparam_callback, eval_callback, video_callback, tbplot_callback])" ] }, { "cell_type": "code", "execution_count": 8, "id": "0bf6ac3e", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T14:39:28.996411Z", "iopub.status.busy": "2024-05-14T14:39:28.996164Z", "iopub.status.idle": "2024-05-14T16:53:32.533566Z", "shell.execute_reply": "2024-05-14T16:53:32.532603Z" }, "papermill": { "duration": 8043.543948, "end_time": "2024-05-14T16:53:32.535728", "exception": false, "start_time": "2024-05-14T14:39:28.991780", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Logging to ././tb/_1\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/opt/conda/lib/python3.10/site-packages/stable_baselines3/common/callbacks.py:403: UserWarning: Training and eval env are not of the same type != \n", " warnings.warn(\"Training and eval env are not of the same type\" f\"{self.training_env} != {self.eval_env}\")\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 106 |\n", "| iterations | 100 |\n", "| time_elapsed | 4 |\n", "| total_timesteps | 500 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | -0.0132 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.011 |\n", "| value_loss | 5.01e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 455 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 137 |\n", "| iterations | 200 |\n", "| time_elapsed | 7 |\n", "| total_timesteps | 1000 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | -0.774 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0162 |\n", "| value_loss | 0.000132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 152 |\n", "| iterations | 300 |\n", "| time_elapsed | 9 |\n", "| total_timesteps | 1500 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | -5.84 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00152 |\n", "| value_loss | 1.26e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 411 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 161 |\n", "| iterations | 400 |\n", "| time_elapsed | 12 |\n", "| total_timesteps | 2000 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | 0.00325 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.703 |\n", "| value_loss | 0.382 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 428 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 167 |\n", "| iterations | 500 |\n", "| time_elapsed | 14 |\n", "| total_timesteps | 2500 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | -0.0954 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.018 |\n", "| value_loss | 0.000125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 171 |\n", "| iterations | 600 |\n", "| time_elapsed | 17 |\n", "| total_timesteps | 3000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0.0864 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0205 |\n", "| value_loss | 0.000136 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 174 |\n", "| iterations | 700 |\n", "| time_elapsed | 20 |\n", "| total_timesteps | 3500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -0.0631 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0122 |\n", "| value_loss | 0.00051 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 175 |\n", "| iterations | 800 |\n", "| time_elapsed | 22 |\n", "| total_timesteps | 4000 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | 0.00592 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0162 |\n", "| value_loss | 0.000125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 420 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 177 |\n", "| iterations | 900 |\n", "| time_elapsed | 25 |\n", "| total_timesteps | 4500 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | -0.00494 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0179 |\n", "| value_loss | 0.000135 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 178 |\n", "| iterations | 1000 |\n", "| time_elapsed | 27 |\n", "| total_timesteps | 5000 |\n", "| train/ | |\n", "| entropy_loss | -1.5 |\n", "| explained_variance | 0.0277 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0216 |\n", "| value_loss | 0.000256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 179 |\n", "| iterations | 1100 |\n", "| time_elapsed | 30 |\n", "| total_timesteps | 5500 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | -0.0412 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.02 |\n", "| value_loss | 0.000183 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 180 |\n", "| iterations | 1200 |\n", "| time_elapsed | 33 |\n", "| total_timesteps | 6000 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | -1.36e+05 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00026 |\n", "| value_loss | 7.17e-08 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 181 |\n", "| iterations | 1300 |\n", "| time_elapsed | 35 |\n", "| total_timesteps | 6500 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | -1.35e+05 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.000355 |\n", "| value_loss | 2.79e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 417 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 181 |\n", "| iterations | 1400 |\n", "| time_elapsed | 38 |\n", "| total_timesteps | 7000 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | 0.0745 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0122 |\n", "| value_loss | 6.94e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 416 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 181 |\n", "| iterations | 1500 |\n", "| time_elapsed | 41 |\n", "| total_timesteps | 7500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -5.94 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00255 |\n", "| value_loss | 3.32e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 182 |\n", "| iterations | 1600 |\n", "| time_elapsed | 43 |\n", "| total_timesteps | 8000 |\n", "| train/ | |\n", "| entropy_loss | -0.709 |\n", "| explained_variance | -0.00824 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.99 |\n", "| value_loss | 1.74 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 423 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 182 |\n", "| iterations | 1700 |\n", "| time_elapsed | 46 |\n", "| total_timesteps | 8500 |\n", "| train/ | |\n", "| entropy_loss | -1.51 |\n", "| explained_variance | 0.000707 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.46 |\n", "| value_loss | 1.17 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 428 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 183 |\n", "| iterations | 1800 |\n", "| time_elapsed | 49 |\n", "| total_timesteps | 9000 |\n", "| train/ | |\n", "| entropy_loss | -1.42 |\n", "| explained_variance | -0.066 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0109 |\n", "| value_loss | 7.25e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 183 |\n", "| iterations | 1900 |\n", "| time_elapsed | 51 |\n", "| total_timesteps | 9500 |\n", "| train/ | |\n", "| entropy_loss | -0.845 |\n", "| explained_variance | -0.00447 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.097 |\n", "| value_loss | 0.366 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 2000 |\n", "| time_elapsed | 54 |\n", "| total_timesteps | 10000 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | -1.37e+03 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00143 |\n", "| value_loss | 9.6e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 436 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 2100 |\n", "| time_elapsed | 56 |\n", "| total_timesteps | 10500 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | -2.62 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00169 |\n", "| value_loss | 3.75e-06 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 2200 |\n", "| time_elapsed | 59 |\n", "| total_timesteps | 11000 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -1.79 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000226 |\n", "| value_loss | 4.92e-08 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 450 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 2300 |\n", "| time_elapsed | 62 |\n", "| total_timesteps | 11500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | 0.202 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0143 |\n", "| value_loss | 8.97e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 2400 |\n", "| time_elapsed | 64 |\n", "| total_timesteps | 12000 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | 0.0616 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0113 |\n", "| value_loss | 6.16e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 444 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 2500 |\n", "| time_elapsed | 67 |\n", "| total_timesteps | 12500 |\n", "| train/ | |\n", "| entropy_loss | -0.0639 |\n", "| explained_variance | 0.00382 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00124 |\n", "| value_loss | 0.155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 2600 |\n", "| time_elapsed | 69 |\n", "| total_timesteps | 13000 |\n", "| train/ | |\n", "| entropy_loss | -1.55 |\n", "| explained_variance | -0.00718 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.47 |\n", "| value_loss | 0.914 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 443 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 2700 |\n", "| time_elapsed | 72 |\n", "| total_timesteps | 13500 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | -0.00157 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.228 |\n", "| value_loss | 0.195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 2800 |\n", "| time_elapsed | 74 |\n", "| total_timesteps | 14000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -23.8 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -6e-05 |\n", "| value_loss | 2.79e-08 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 2900 |\n", "| time_elapsed | 77 |\n", "| total_timesteps | 14500 |\n", "| train/ | |\n", "| entropy_loss | -1.5 |\n", "| explained_variance | -0.0602 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00265 |\n", "| value_loss | 5.45e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 3000 |\n", "| time_elapsed | 80 |\n", "| total_timesteps | 15000 |\n", "| train/ | |\n", "| entropy_loss | -1.55 |\n", "| explained_variance | -0.00776 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 3100 |\n", "| time_elapsed | 82 |\n", "| total_timesteps | 15500 |\n", "| train/ | |\n", "| entropy_loss | -0.178 |\n", "| explained_variance | -45.9 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.79e-06 |\n", "| value_loss | 4.32e-09 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 440 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 3200 |\n", "| time_elapsed | 85 |\n", "| total_timesteps | 16000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0.203 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0171 |\n", "| value_loss | 0.000215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 439 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3300 |\n", "| time_elapsed | 87 |\n", "| total_timesteps | 16500 |\n", "| train/ | |\n", "| entropy_loss | -1.52 |\n", "| explained_variance | 0.723 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0027 |\n", "| value_loss | 3.7e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 440 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3400 |\n", "| time_elapsed | 90 |\n", "| total_timesteps | 17000 |\n", "| train/ | |\n", "| entropy_loss | -1.55 |\n", "| explained_variance | -34.1 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00595 |\n", "| value_loss | 2.05e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3500 |\n", "| time_elapsed | 92 |\n", "| total_timesteps | 17500 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0139 |\n", "| value_loss | 9.3e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3600 |\n", "| time_elapsed | 95 |\n", "| total_timesteps | 18000 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | 0.0341 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0161 |\n", "| value_loss | 0.000122 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3700 |\n", "| time_elapsed | 98 |\n", "| total_timesteps | 18500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -100 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00164 |\n", "| value_loss | 1.73e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3800 |\n", "| time_elapsed | 100 |\n", "| total_timesteps | 19000 |\n", "| train/ | |\n", "| entropy_loss | -0.836 |\n", "| explained_variance | 0.0178 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.018 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 439 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 3900 |\n", "| time_elapsed | 103 |\n", "| total_timesteps | 19500 |\n", "| train/ | |\n", "| entropy_loss | -1.55 |\n", "| explained_variance | 0.133 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0152 |\n", "| value_loss | 7.41e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 440 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 4000 |\n", "| time_elapsed | 105 |\n", "| total_timesteps | 20000 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | 0.0084 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.63 |\n", "| value_loss | 0.947 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4100 |\n", "| time_elapsed | 108 |\n", "| total_timesteps | 20500 |\n", "| train/ | |\n", "| entropy_loss | -0.241 |\n", "| explained_variance | 0.0138 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00396 |\n", "| value_loss | 0.00842 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4200 |\n", "| time_elapsed | 110 |\n", "| total_timesteps | 21000 |\n", "| train/ | |\n", "| entropy_loss | -0.965 |\n", "| explained_variance | 0.00993 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0183 |\n", "| value_loss | 0.000601 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4300 |\n", "| time_elapsed | 113 |\n", "| total_timesteps | 21500 |\n", "| train/ | |\n", "| entropy_loss | -0.443 |\n", "| explained_variance | 0.0419 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0188 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4400 |\n", "| time_elapsed | 116 |\n", "| total_timesteps | 22000 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 0.034 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00496 |\n", "| value_loss | 5.16e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4500 |\n", "| time_elapsed | 118 |\n", "| total_timesteps | 22500 |\n", "| train/ | |\n", "| entropy_loss | -1.54 |\n", "| explained_variance | 0.00387 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0118 |\n", "| value_loss | 4.92e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4600 |\n", "| time_elapsed | 121 |\n", "| total_timesteps | 23000 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | 0.0921 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00986 |\n", "| value_loss | 4.99e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 455 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4700 |\n", "| time_elapsed | 123 |\n", "| total_timesteps | 23500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -0.000367 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.39 |\n", "| value_loss | 3.1 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 455 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4800 |\n", "| time_elapsed | 126 |\n", "| total_timesteps | 24000 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | -0.0291 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0218 |\n", "| value_loss | 0.000252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 457 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 4900 |\n", "| time_elapsed | 129 |\n", "| total_timesteps | 24500 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | 0.179 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00737 |\n", "| value_loss | 2.68e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 460 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5000 |\n", "| time_elapsed | 131 |\n", "| total_timesteps | 25000 |\n", "| train/ | |\n", "| entropy_loss | -0.187 |\n", "| explained_variance | -0.6 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.000281 |\n", "| value_loss | 8.78e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 455 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5100 |\n", "| time_elapsed | 134 |\n", "| total_timesteps | 25500 |\n", "| train/ | |\n", "| entropy_loss | -0.0313 |\n", "| explained_variance | -2 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.21e-06 |\n", "| value_loss | 2.38e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 453 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5200 |\n", "| time_elapsed | 137 |\n", "| total_timesteps | 26000 |\n", "| train/ | |\n", "| entropy_loss | -0.0245 |\n", "| explained_variance | -274 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -3.33e-05 |\n", "| value_loss | 0.000145 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5300 |\n", "| time_elapsed | 139 |\n", "| total_timesteps | 26500 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | -0.0324 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0157 |\n", "| value_loss | 0.000109 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5400 |\n", "| time_elapsed | 142 |\n", "| total_timesteps | 27000 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -0.00192 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.25 |\n", "| value_loss | 0.734 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5500 |\n", "| time_elapsed | 144 |\n", "| total_timesteps | 27500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -0.0449 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0168 |\n", "| value_loss | 0.000173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5600 |\n", "| time_elapsed | 147 |\n", "| total_timesteps | 28000 |\n", "| train/ | |\n", "| entropy_loss | -1.61 |\n", "| explained_variance | 0.00227 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0133 |\n", "| value_loss | 9.27e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 444 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 5700 |\n", "| time_elapsed | 150 |\n", "| total_timesteps | 28500 |\n", "| train/ | |\n", "| entropy_loss | -1.53 |\n", "| explained_variance | -0.0242 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.024 |\n", "| value_loss | 0.000232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 5800 |\n", "| time_elapsed | 152 |\n", "| total_timesteps | 29000 |\n", "| train/ | |\n", "| entropy_loss | -1.41 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00455 |\n", "| value_loss | 1.59e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 5900 |\n", "| time_elapsed | 155 |\n", "| total_timesteps | 29500 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | 0.00656 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.022 |\n", "| value_loss | 0.000219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 450 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6000 |\n", "| time_elapsed | 157 |\n", "| total_timesteps | 30000 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | 0.0198 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0232 |\n", "| value_loss | 0.00023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6100 |\n", "| time_elapsed | 160 |\n", "| total_timesteps | 30500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | -0.0101 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.57 |\n", "| value_loss | 0.936 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6200 |\n", "| time_elapsed | 163 |\n", "| total_timesteps | 31000 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | 0.0475 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.000592 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 449 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6300 |\n", "| time_elapsed | 165 |\n", "| total_timesteps | 31500 |\n", "| train/ | |\n", "| entropy_loss | -0.422 |\n", "| explained_variance | -0.246 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0147 |\n", "| value_loss | 0.000843 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 450 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6400 |\n", "| time_elapsed | 168 |\n", "| total_timesteps | 32000 |\n", "| train/ | |\n", "| entropy_loss | -0.967 |\n", "| explained_variance | -0.00343 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.614 |\n", "| value_loss | 1.31 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 450 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6500 |\n", "| time_elapsed | 170 |\n", "| total_timesteps | 32500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -0.103 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0068 |\n", "| value_loss | 5.54e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6600 |\n", "| time_elapsed | 173 |\n", "| total_timesteps | 33000 |\n", "| train/ | |\n", "| entropy_loss | -1.45 |\n", "| explained_variance | 0.0128 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0131 |\n", "| value_loss | 0.000192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6700 |\n", "| time_elapsed | 176 |\n", "| total_timesteps | 33500 |\n", "| train/ | |\n", "| entropy_loss | -1.53 |\n", "| explained_variance | 0.00121 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0189 |\n", "| value_loss | 0.000124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6800 |\n", "| time_elapsed | 178 |\n", "| total_timesteps | 34000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0.00518 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.37 |\n", "| value_loss | 0.579 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 6900 |\n", "| time_elapsed | 181 |\n", "| total_timesteps | 34500 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 4.89e-05 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.243 |\n", "| value_loss | 0.376 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 445 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7000 |\n", "| time_elapsed | 183 |\n", "| total_timesteps | 35000 |\n", "| train/ | |\n", "| entropy_loss | -1.46 |\n", "| explained_variance | 0.000902 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.604 |\n", "| value_loss | 0.392 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 445 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7100 |\n", "| time_elapsed | 186 |\n", "| total_timesteps | 35500 |\n", "| train/ | |\n", "| entropy_loss | -1.39 |\n", "| explained_variance | 0.000447 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0199 |\n", "| value_loss | 0.000329 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7200 |\n", "| time_elapsed | 188 |\n", "| total_timesteps | 36000 |\n", "| train/ | |\n", "| entropy_loss | -1.5 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0134 |\n", "| value_loss | 8.9e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7300 |\n", "| time_elapsed | 191 |\n", "| total_timesteps | 36500 |\n", "| train/ | |\n", "| entropy_loss | -0.669 |\n", "| explained_variance | 0.00212 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00427 |\n", "| value_loss | 4.88e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7400 |\n", "| time_elapsed | 194 |\n", "| total_timesteps | 37000 |\n", "| train/ | |\n", "| entropy_loss | -0.241 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.59e-05 |\n", "| value_loss | 1.29e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 447 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7500 |\n", "| time_elapsed | 196 |\n", "| total_timesteps | 37500 |\n", "| train/ | |\n", "| entropy_loss | -0.188 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -9.49e-07 |\n", "| value_loss | 8.48e-10 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7600 |\n", "| time_elapsed | 199 |\n", "| total_timesteps | 38000 |\n", "| train/ | |\n", "| entropy_loss | -0.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -2.41e-05 |\n", "| value_loss | 1.67e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 445 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7700 |\n", "| time_elapsed | 201 |\n", "| total_timesteps | 38500 |\n", "| train/ | |\n", "| entropy_loss | -0.0847 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000694 |\n", "| value_loss | 4.22e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 443 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7800 |\n", "| time_elapsed | 204 |\n", "| total_timesteps | 39000 |\n", "| train/ | |\n", "| entropy_loss | -0.0545 |\n", "| explained_variance | 1 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.44e-07 |\n", "| value_loss | 4.5e-10 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 7900 |\n", "| time_elapsed | 206 |\n", "| total_timesteps | 39500 |\n", "| train/ | |\n", "| entropy_loss | -0.045 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -2.48e-06 |\n", "| value_loss | 1.82e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8000 |\n", "| time_elapsed | 209 |\n", "| total_timesteps | 40000 |\n", "| train/ | |\n", "| entropy_loss | -0.0419 |\n", "| explained_variance | -5.47e+04 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -9.96e-08 |\n", "| value_loss | 9.79e-10 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 440 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 8100 |\n", "| time_elapsed | 212 |\n", "| total_timesteps | 40500 |\n", "| train/ | |\n", "| entropy_loss | -0.129 |\n", "| explained_variance | 0.0019 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00862 |\n", "| value_loss | 0.387 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 439 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8200 |\n", "| time_elapsed | 214 |\n", "| total_timesteps | 41000 |\n", "| train/ | |\n", "| entropy_loss | -0.143 |\n", "| explained_variance | -53 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -7.83e-06 |\n", "| value_loss | 1.27e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 438 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8300 |\n", "| time_elapsed | 217 |\n", "| total_timesteps | 41500 |\n", "| train/ | |\n", "| entropy_loss | -0.0933 |\n", "| explained_variance | -3.23 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 5.62e-06 |\n", "| value_loss | 1.78e-07 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 438 |\n", "| ep_rew_mean | 14.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8400 |\n", "| time_elapsed | 220 |\n", "| total_timesteps | 42000 |\n", "| train/ | |\n", "| entropy_loss | -0.191 |\n", "| explained_variance | -0.0566 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.13e-05 |\n", "| value_loss | 1.76e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 437 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8500 |\n", "| time_elapsed | 222 |\n", "| total_timesteps | 42500 |\n", "| train/ | |\n", "| entropy_loss | -0.158 |\n", "| explained_variance | -5.6e-05 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000382 |\n", "| value_loss | 0.000229 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 437 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8600 |\n", "| time_elapsed | 225 |\n", "| total_timesteps | 43000 |\n", "| train/ | |\n", "| entropy_loss | -0.0806 |\n", "| explained_variance | -0.0122 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -5.8e-05 |\n", "| value_loss | 2.71e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 437 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8700 |\n", "| time_elapsed | 227 |\n", "| total_timesteps | 43500 |\n", "| train/ | |\n", "| entropy_loss | -0.0564 |\n", "| explained_variance | -2.04e+03 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.32e-06 |\n", "| value_loss | 6.33e-08 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 436 |\n", "| ep_rew_mean | 14.3 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8800 |\n", "| time_elapsed | 230 |\n", "| total_timesteps | 44000 |\n", "| train/ | |\n", "| entropy_loss | -0.0384 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -8.72e-07 |\n", "| value_loss | 3.43e-08 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 434 |\n", "| ep_rew_mean | 14.2 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 8900 |\n", "| time_elapsed | 233 |\n", "| total_timesteps | 44500 |\n", "| train/ | |\n", "| entropy_loss | -0.0379 |\n", "| explained_variance | -0.988 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.8e-06 |\n", "| value_loss | 1.49e-07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 435 |\n", "| ep_rew_mean | 14.2 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 9000 |\n", "| time_elapsed | 235 |\n", "| total_timesteps | 45000 |\n", "| train/ | |\n", "| entropy_loss | -0.0553 |\n", "| explained_variance | -1.19 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.83e-06 |\n", "| value_loss | 6.38e-08 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 433 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 9100 |\n", "| time_elapsed | 238 |\n", "| total_timesteps | 45500 |\n", "| train/ | |\n", "| entropy_loss | -0.113 |\n", "| explained_variance | 0.2 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -7.4e-05 |\n", "| value_loss | 1.9e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 190 |\n", "| iterations | 9200 |\n", "| time_elapsed | 240 |\n", "| total_timesteps | 46000 |\n", "| train/ | |\n", "| entropy_loss | -0.101 |\n", "| explained_variance | -81.2 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -3.21e-05 |\n", "| value_loss | 5.6e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9300 |\n", "| time_elapsed | 243 |\n", "| total_timesteps | 46500 |\n", "| train/ | |\n", "| entropy_loss | -0.0339 |\n", "| explained_variance | -7.2e+03 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -6.27e-07 |\n", "| value_loss | 1.07e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9400 |\n", "| time_elapsed | 246 |\n", "| total_timesteps | 47000 |\n", "| train/ | |\n", "| entropy_loss | -0.0571 |\n", "| explained_variance | 0.0575 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -3.65e-05 |\n", "| value_loss | 2.39e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9500 |\n", "| time_elapsed | 248 |\n", "| total_timesteps | 47500 |\n", "| train/ | |\n", "| entropy_loss | -0.0319 |\n", "| explained_variance | 0.378 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.01e-07 |\n", "| value_loss | 3.51e-09 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9600 |\n", "| time_elapsed | 251 |\n", "| total_timesteps | 48000 |\n", "| train/ | |\n", "| entropy_loss | -0.0398 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.68e-07 |\n", "| value_loss | 1.17e-09 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9700 |\n", "| time_elapsed | 253 |\n", "| total_timesteps | 48500 |\n", "| train/ | |\n", "| entropy_loss | -0.264 |\n", "| explained_variance | -3.79 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000418 |\n", "| value_loss | 9.51e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9800 |\n", "| time_elapsed | 256 |\n", "| total_timesteps | 49000 |\n", "| train/ | |\n", "| entropy_loss | -0.054 |\n", "| explained_variance | -261 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 3.09e-06 |\n", "| value_loss | 5.02e-07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 429 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 9900 |\n", "| time_elapsed | 258 |\n", "| total_timesteps | 49500 |\n", "| train/ | |\n", "| entropy_loss | -0.09 |\n", "| explained_variance | -14.2 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 4.4e-06 |\n", "| value_loss | 1.42e-07 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 429 |\n", "| ep_rew_mean | 12.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10000 |\n", "| time_elapsed | 261 |\n", "| total_timesteps | 50000 |\n", "| train/ | |\n", "| entropy_loss | -0.0174 |\n", "| explained_variance | 0.452 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.48e-06 |\n", "| value_loss | 5.39e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 428 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10100 |\n", "| time_elapsed | 264 |\n", "| total_timesteps | 50500 |\n", "| train/ | |\n", "| entropy_loss | -0.00939 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -5.94e-08 |\n", "| value_loss | 3.91e-09 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 428 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10200 |\n", "| time_elapsed | 266 |\n", "| total_timesteps | 51000 |\n", "| train/ | |\n", "| entropy_loss | -0.0105 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.44e-07 |\n", "| value_loss | 1.49e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 424 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10300 |\n", "| time_elapsed | 269 |\n", "| total_timesteps | 51500 |\n", "| train/ | |\n", "| entropy_loss | -0.0477 |\n", "| explained_variance | -12.6 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -5.1e-05 |\n", "| value_loss | 9.61e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 423 |\n", "| ep_rew_mean | 11.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10400 |\n", "| time_elapsed | 271 |\n", "| total_timesteps | 52000 |\n", "| train/ | |\n", "| entropy_loss | -0.0348 |\n", "| explained_variance | -116 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.86e-07 |\n", "| value_loss | 5.44e-09 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 417 |\n", "| ep_rew_mean | 10.9 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10500 |\n", "| time_elapsed | 274 |\n", "| total_timesteps | 52500 |\n", "| train/ | |\n", "| entropy_loss | -0.0508 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.29e-06 |\n", "| value_loss | 4.14e-08 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 416 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10600 |\n", "| time_elapsed | 276 |\n", "| total_timesteps | 53000 |\n", "| train/ | |\n", "| entropy_loss | -0.0241 |\n", "| explained_variance | -3.17 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.54e-06 |\n", "| value_loss | 2.68e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 416 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10700 |\n", "| time_elapsed | 279 |\n", "| total_timesteps | 53500 |\n", "| train/ | |\n", "| entropy_loss | -0.019 |\n", "| explained_variance | 0.368 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.06e-07 |\n", "| value_loss | 9.54e-09 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10800 |\n", "| time_elapsed | 282 |\n", "| total_timesteps | 54000 |\n", "| train/ | |\n", "| entropy_loss | -0.034 |\n", "| explained_variance | 0.429 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.07e-05 |\n", "| value_loss | 7.07e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 10900 |\n", "| time_elapsed | 284 |\n", "| total_timesteps | 54500 |\n", "| train/ | |\n", "| entropy_loss | -0.0317 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -2.57e-06 |\n", "| value_loss | 4.86e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11000 |\n", "| time_elapsed | 287 |\n", "| total_timesteps | 55000 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | 0.00194 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.16 |\n", "| value_loss | 0.74 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11100 |\n", "| time_elapsed | 289 |\n", "| total_timesteps | 55500 |\n", "| train/ | |\n", "| entropy_loss | -0.143 |\n", "| explained_variance | -0.000642 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.12 |\n", "| value_loss | 2.09 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11200 |\n", "| time_elapsed | 292 |\n", "| total_timesteps | 56000 |\n", "| train/ | |\n", "| entropy_loss | -0.0776 |\n", "| explained_variance | -90.7 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.05e-05 |\n", "| value_loss | 1.48e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.87 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11300 |\n", "| time_elapsed | 295 |\n", "| total_timesteps | 56500 |\n", "| train/ | |\n", "| entropy_loss | -0.0516 |\n", "| explained_variance | 0.77 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -7.31e-05 |\n", "| value_loss | 0.000303 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.78 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11400 |\n", "| time_elapsed | 297 |\n", "| total_timesteps | 57000 |\n", "| train/ | |\n", "| entropy_loss | -0.0993 |\n", "| explained_variance | -0.0146 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -3.6e-05 |\n", "| value_loss | 6.39e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.7 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11500 |\n", "| time_elapsed | 300 |\n", "| total_timesteps | 57500 |\n", "| train/ | |\n", "| entropy_loss | -0.033 |\n", "| explained_variance | -382 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.06e-06 |\n", "| value_loss | 1.84e-07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 9.38 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11600 |\n", "| time_elapsed | 303 |\n", "| total_timesteps | 58000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -0.445 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.102 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 9.38 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11700 |\n", "| time_elapsed | 305 |\n", "| total_timesteps | 58500 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | 0.192 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.000786 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 9.86 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11800 |\n", "| time_elapsed | 308 |\n", "| total_timesteps | 59000 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | -0.0214 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00998 |\n", "| value_loss | 4.7e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 9.91 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 11900 |\n", "| time_elapsed | 310 |\n", "| total_timesteps | 59500 |\n", "| train/ | |\n", "| entropy_loss | -0.487 |\n", "| explained_variance | -0.0525 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00578 |\n", "| value_loss | 3.14e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.86 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12000 |\n", "| time_elapsed | 313 |\n", "| total_timesteps | 60000 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | 0.0409 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0317 |\n", "| value_loss | 0.000422 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.84 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12100 |\n", "| time_elapsed | 315 |\n", "| total_timesteps | 60500 |\n", "| train/ | |\n", "| entropy_loss | -0.0978 |\n", "| explained_variance | -9.45 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.45e-05 |\n", "| value_loss | 1.87e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 9.81 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12200 |\n", "| time_elapsed | 318 |\n", "| total_timesteps | 61000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00445 |\n", "| value_loss | 1.64e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 9.71 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12300 |\n", "| time_elapsed | 321 |\n", "| total_timesteps | 61500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0.00419 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0029 |\n", "| value_loss | 7.08e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 9.69 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12400 |\n", "| time_elapsed | 323 |\n", "| total_timesteps | 62000 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | 0.000323 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.91 |\n", "| value_loss | 0.574 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12500 |\n", "| time_elapsed | 326 |\n", "| total_timesteps | 62500 |\n", "| train/ | |\n", "| entropy_loss | -0.418 |\n", "| explained_variance | 0.0173 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0006 |\n", "| value_loss | 5.04e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12600 |\n", "| time_elapsed | 328 |\n", "| total_timesteps | 63000 |\n", "| train/ | |\n", "| entropy_loss | -0.365 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000989 |\n", "| value_loss | 0.000192 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 413 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12700 |\n", "| time_elapsed | 331 |\n", "| total_timesteps | 63500 |\n", "| train/ | |\n", "| entropy_loss | -0.177 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 5.04e-07 |\n", "| value_loss | 3.02e-10 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12800 |\n", "| time_elapsed | 334 |\n", "| total_timesteps | 64000 |\n", "| train/ | |\n", "| entropy_loss | -0.0954 |\n", "| explained_variance | -16.4 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -3.77e-06 |\n", "| value_loss | 9.8e-08 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 408 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 12900 |\n", "| time_elapsed | 336 |\n", "| total_timesteps | 64500 |\n", "| train/ | |\n", "| entropy_loss | -0.0705 |\n", "| explained_variance | -0.0405 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00832 |\n", "| value_loss | 0.809 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 408 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13000 |\n", "| time_elapsed | 339 |\n", "| total_timesteps | 65000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0.441 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.859 |\n", "| value_loss | 0.999 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 10 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13100 |\n", "| time_elapsed | 341 |\n", "| total_timesteps | 65500 |\n", "| train/ | |\n", "| entropy_loss | -1.47 |\n", "| explained_variance | 0.0912 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00137 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13200 |\n", "| time_elapsed | 344 |\n", "| total_timesteps | 66000 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | 0.0208 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0135 |\n", "| value_loss | 9.95e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13300 |\n", "| time_elapsed | 347 |\n", "| total_timesteps | 66500 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 0.0435 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0105 |\n", "| value_loss | 4.23e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 408 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13400 |\n", "| time_elapsed | 349 |\n", "| total_timesteps | 67000 |\n", "| train/ | |\n", "| entropy_loss | -1.48 |\n", "| explained_variance | -0.0235 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00701 |\n", "| value_loss | 3.39e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 410 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13500 |\n", "| time_elapsed | 352 |\n", "| total_timesteps | 67500 |\n", "| train/ | |\n", "| entropy_loss | -1.49 |\n", "| explained_variance | 0.0157 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.515 |\n", "| value_loss | 0.369 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13600 |\n", "| time_elapsed | 354 |\n", "| total_timesteps | 68000 |\n", "| train/ | |\n", "| entropy_loss | -0.87 |\n", "| explained_variance | 0.0187 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0568 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 411 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13700 |\n", "| time_elapsed | 357 |\n", "| total_timesteps | 68500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0.0684 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0084 |\n", "| value_loss | 9.15e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 411 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13800 |\n", "| time_elapsed | 360 |\n", "| total_timesteps | 69000 |\n", "| train/ | |\n", "| entropy_loss | -0.493 |\n", "| explained_variance | -0.00582 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00183 |\n", "| value_loss | 0.000299 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 410 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 13900 |\n", "| time_elapsed | 362 |\n", "| total_timesteps | 69500 |\n", "| train/ | |\n", "| entropy_loss | -0.271 |\n", "| explained_variance | 0.0349 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -8.32e-05 |\n", "| value_loss | 2.85e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 409 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14000 |\n", "| time_elapsed | 365 |\n", "| total_timesteps | 70000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | -0.00775 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0206 |\n", "| value_loss | 0.000471 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14100 |\n", "| time_elapsed | 367 |\n", "| total_timesteps | 70500 |\n", "| train/ | |\n", "| entropy_loss | -0.115 |\n", "| explained_variance | -6.49 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000153 |\n", "| value_loss | 6.92e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 9.98 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14200 |\n", "| time_elapsed | 370 |\n", "| total_timesteps | 71000 |\n", "| train/ | |\n", "| entropy_loss | -0.113 |\n", "| explained_variance | -5.56 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -6e-06 |\n", "| value_loss | 2.99e-07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.86 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14300 |\n", "| time_elapsed | 373 |\n", "| total_timesteps | 71500 |\n", "| train/ | |\n", "| entropy_loss | -0.449 |\n", "| explained_variance | -0.053 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00042 |\n", "| value_loss | 1.59e-06 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.7 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14400 |\n", "| time_elapsed | 375 |\n", "| total_timesteps | 72000 |\n", "| train/ | |\n", "| entropy_loss | -0.259 |\n", "| explained_variance | 0.0448 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000187 |\n", "| value_loss | 1.37e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 9.68 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14500 |\n", "| time_elapsed | 378 |\n", "| total_timesteps | 72500 |\n", "| train/ | |\n", "| entropy_loss | -0.296 |\n", "| explained_variance | -0.0444 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0125 |\n", "| value_loss | 0.192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 9.65 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14600 |\n", "| time_elapsed | 380 |\n", "| total_timesteps | 73000 |\n", "| train/ | |\n", "| entropy_loss | -0.188 |\n", "| explained_variance | -0.146 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00074 |\n", "| value_loss | 0.000485 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.73 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14700 |\n", "| time_elapsed | 383 |\n", "| total_timesteps | 73500 |\n", "| train/ | |\n", "| entropy_loss | -0.327 |\n", "| explained_variance | -0.00902 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00102 |\n", "| value_loss | 0.000241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 9.73 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14800 |\n", "| time_elapsed | 386 |\n", "| total_timesteps | 74000 |\n", "| train/ | |\n", "| entropy_loss | -0.55 |\n", "| explained_variance | 0.0313 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00213 |\n", "| value_loss | 0.000248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.77 |\n", "| time/ | |\n", "| fps | 191 |\n", "| iterations | 14900 |\n", "| time_elapsed | 388 |\n", "| total_timesteps | 74500 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | -0.267 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00528 |\n", "| value_loss | 1.78e-05 |\n", "------------------------------------\n", "Eval num_timesteps=75000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "-------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 75000 |\n", "| train/ | |\n", "| entropy_loss | -0.101 |\n", "| explained_variance | -72 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000101 |\n", "| value_loss | 4.75e-05 |\n", "-------------------------------------\n", "New best mean reward!\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.68 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15000 |\n", "| time_elapsed | 402 |\n", "| total_timesteps | 75000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 9.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15100 |\n", "| time_elapsed | 404 |\n", "| total_timesteps | 75500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0.107 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.000408 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 406 |\n", "| ep_rew_mean | 9.55 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15200 |\n", "| time_elapsed | 407 |\n", "| total_timesteps | 76000 |\n", "| train/ | |\n", "| entropy_loss | -1.52 |\n", "| explained_variance | -0.0484 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0206 |\n", "| value_loss | 0.000225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 9.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15300 |\n", "| time_elapsed | 410 |\n", "| total_timesteps | 76500 |\n", "| train/ | |\n", "| entropy_loss | -1.4 |\n", "| explained_variance | 0.509 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.727 |\n", "| value_loss | 0.366 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 9.43 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15400 |\n", "| time_elapsed | 412 |\n", "| total_timesteps | 77000 |\n", "| train/ | |\n", "| entropy_loss | -0.687 |\n", "| explained_variance | -0.0212 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0101 |\n", "| value_loss | 0.000613 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 9.42 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15500 |\n", "| time_elapsed | 415 |\n", "| total_timesteps | 77500 |\n", "| train/ | |\n", "| entropy_loss | -0.936 |\n", "| explained_variance | -0.038 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0046 |\n", "| value_loss | 2.49e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 9.37 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15600 |\n", "| time_elapsed | 418 |\n", "| total_timesteps | 78000 |\n", "| train/ | |\n", "| entropy_loss | -0.201 |\n", "| explained_variance | -0.078 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.678 |\n", "| value_loss | 0.648 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 9.38 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15700 |\n", "| time_elapsed | 420 |\n", "| total_timesteps | 78500 |\n", "| train/ | |\n", "| entropy_loss | -0.323 |\n", "| explained_variance | -36.8 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000301 |\n", "| value_loss | 3.05e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 9.39 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15800 |\n", "| time_elapsed | 423 |\n", "| total_timesteps | 79000 |\n", "| train/ | |\n", "| entropy_loss | -0.266 |\n", "| explained_variance | -0.00674 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000138 |\n", "| value_loss | 5.29e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 9.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 15900 |\n", "| time_elapsed | 425 |\n", "| total_timesteps | 79500 |\n", "| train/ | |\n", "| entropy_loss | -1.6 |\n", "| explained_variance | 0.0184 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0237 |\n", "| value_loss | 0.000271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 9.62 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16000 |\n", "| time_elapsed | 428 |\n", "| total_timesteps | 80000 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | -0.0433 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0305 |\n", "| value_loss | 0.000477 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 9.71 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16100 |\n", "| time_elapsed | 431 |\n", "| total_timesteps | 80500 |\n", "| train/ | |\n", "| entropy_loss | -0.87 |\n", "| explained_variance | -0.0604 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0111 |\n", "| value_loss | 0.000729 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 9.95 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16200 |\n", "| time_elapsed | 433 |\n", "| total_timesteps | 81000 |\n", "| train/ | |\n", "| entropy_loss | -0.867 |\n", "| explained_variance | -0.0492 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.171 |\n", "| value_loss | 0.415 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16300 |\n", "| time_elapsed | 436 |\n", "| total_timesteps | 81500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | -0.866 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00196 |\n", "| value_loss | 1.8e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16400 |\n", "| time_elapsed | 438 |\n", "| total_timesteps | 82000 |\n", "| train/ | |\n", "| entropy_loss | -0.971 |\n", "| explained_variance | 0.171 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00605 |\n", "| value_loss | 5.7e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16500 |\n", "| time_elapsed | 441 |\n", "| total_timesteps | 82500 |\n", "| train/ | |\n", "| entropy_loss | -0.996 |\n", "| explained_variance | 0.106 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00131 |\n", "| value_loss | 1.12e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16600 |\n", "| time_elapsed | 444 |\n", "| total_timesteps | 83000 |\n", "| train/ | |\n", "| entropy_loss | -1.04 |\n", "| explained_variance | -0.173 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0187 |\n", "| value_loss | 0.0002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16700 |\n", "| time_elapsed | 446 |\n", "| total_timesteps | 83500 |\n", "| train/ | |\n", "| entropy_loss | -0.882 |\n", "| explained_variance | 0.318 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0112 |\n", "| value_loss | 5.27e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 398 |\n", "| ep_rew_mean | 10.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16800 |\n", "| time_elapsed | 449 |\n", "| total_timesteps | 84000 |\n", "| train/ | |\n", "| entropy_loss | -0.451 |\n", "| explained_variance | 0.0354 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.024 |\n", "| value_loss | 0.00109 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 16900 |\n", "| time_elapsed | 452 |\n", "| total_timesteps | 84500 |\n", "| train/ | |\n", "| entropy_loss | -0.8 |\n", "| explained_variance | -0.0302 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.09 |\n", "| value_loss | 2.07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 17000 |\n", "| time_elapsed | 454 |\n", "| total_timesteps | 85000 |\n", "| train/ | |\n", "| entropy_loss | -0.303 |\n", "| explained_variance | 0.000249 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00144 |\n", "| value_loss | 0.000453 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 17100 |\n", "| time_elapsed | 457 |\n", "| total_timesteps | 85500 |\n", "| train/ | |\n", "| entropy_loss | -0.0504 |\n", "| explained_variance | -8.83 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.32e-05 |\n", "| value_loss | 8.54e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 17200 |\n", "| time_elapsed | 459 |\n", "| total_timesteps | 86000 |\n", "| train/ | |\n", "| entropy_loss | -0.00249 |\n", "| explained_variance | -0.235 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.62e-08 |\n", "| value_loss | 6.06e-09 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17300 |\n", "| time_elapsed | 462 |\n", "| total_timesteps | 86500 |\n", "| train/ | |\n", "| entropy_loss | -0.00351 |\n", "| explained_variance | -3.11 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 8.43e-07 |\n", "| value_loss | 1.17e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17400 |\n", "| time_elapsed | 465 |\n", "| total_timesteps | 87000 |\n", "| train/ | |\n", "| entropy_loss | -0.00819 |\n", "| explained_variance | 0.0723 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.38e-06 |\n", "| value_loss | 2.74e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17500 |\n", "| time_elapsed | 467 |\n", "| total_timesteps | 87500 |\n", "| train/ | |\n", "| entropy_loss | -0.00418 |\n", "| explained_variance | -0.705 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 3.34e-07 |\n", "| value_loss | 7.22e-07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17600 |\n", "| time_elapsed | 470 |\n", "| total_timesteps | 88000 |\n", "| train/ | |\n", "| entropy_loss | -0.0579 |\n", "| explained_variance | -0.213 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.00719 |\n", "| value_loss | 1.67 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17700 |\n", "| time_elapsed | 473 |\n", "| total_timesteps | 88500 |\n", "| train/ | |\n", "| entropy_loss | -0.00663 |\n", "| explained_variance | -10.3 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 7.22e-07 |\n", "| value_loss | 2.35e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17800 |\n", "| time_elapsed | 475 |\n", "| total_timesteps | 89000 |\n", "| train/ | |\n", "| entropy_loss | -0.00567 |\n", "| explained_variance | -1.31 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.73e-07 |\n", "| value_loss | 3.65e-07 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 17900 |\n", "| time_elapsed | 478 |\n", "| total_timesteps | 89500 |\n", "| train/ | |\n", "| entropy_loss | -0.0272 |\n", "| explained_variance | -1.36 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -2.18e-05 |\n", "| value_loss | 4.73e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18000 |\n", "| time_elapsed | 481 |\n", "| total_timesteps | 90000 |\n", "| train/ | |\n", "| entropy_loss | -0.0895 |\n", "| explained_variance | -0.00105 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -7.17e-05 |\n", "| value_loss | 3.13e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18100 |\n", "| time_elapsed | 483 |\n", "| total_timesteps | 90500 |\n", "| train/ | |\n", "| entropy_loss | -0.176 |\n", "| explained_variance | -1.04 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.2e-05 |\n", "| value_loss | 2.51e-06 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18200 |\n", "| time_elapsed | 486 |\n", "| total_timesteps | 91000 |\n", "| train/ | |\n", "| entropy_loss | -0.0805 |\n", "| explained_variance | -4.88 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 6.48e-05 |\n", "| value_loss | 5.8e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18300 |\n", "| time_elapsed | 489 |\n", "| total_timesteps | 91500 |\n", "| train/ | |\n", "| entropy_loss | -0.091 |\n", "| explained_variance | 0.00415 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.000119 |\n", "| value_loss | 8.25e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18400 |\n", "| time_elapsed | 491 |\n", "| total_timesteps | 92000 |\n", "| train/ | |\n", "| entropy_loss | -0.0607 |\n", "| explained_variance | 0.0644 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -8.92e-06 |\n", "| value_loss | 1.15e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18500 |\n", "| time_elapsed | 494 |\n", "| total_timesteps | 92500 |\n", "| train/ | |\n", "| entropy_loss | -0.0311 |\n", "| explained_variance | 0.471 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.02e-05 |\n", "| value_loss | 6.98e-06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18600 |\n", "| time_elapsed | 496 |\n", "| total_timesteps | 93000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -0.084 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00497 |\n", "| value_loss | 2.49e-05 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18700 |\n", "| time_elapsed | 499 |\n", "| total_timesteps | 93500 |\n", "| train/ | |\n", "| entropy_loss | -0.0158 |\n", "| explained_variance | -71.2 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.89e-07 |\n", "| value_loss | 1.67e-06 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18800 |\n", "| time_elapsed | 501 |\n", "| total_timesteps | 94000 |\n", "| train/ | |\n", "| entropy_loss | -0.0146 |\n", "| explained_variance | -2.21 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.17e-06 |\n", "| value_loss | 9.43e-07 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 18900 |\n", "| time_elapsed | 504 |\n", "| total_timesteps | 94500 |\n", "| train/ | |\n", "| entropy_loss | -0.103 |\n", "| explained_variance | 0.258 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.000233 |\n", "| value_loss | 0.000192 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19000 |\n", "| time_elapsed | 507 |\n", "| total_timesteps | 95000 |\n", "| train/ | |\n", "| entropy_loss | -0.0208 |\n", "| explained_variance | -19.5 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -8.31e-06 |\n", "| value_loss | 1.07e-05 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19100 |\n", "| time_elapsed | 509 |\n", "| total_timesteps | 95500 |\n", "| train/ | |\n", "| entropy_loss | -0.00601 |\n", "| explained_variance | -1.63e+03 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -4.46e-07 |\n", "| value_loss | 9.27e-07 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 398 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19200 |\n", "| time_elapsed | 512 |\n", "| total_timesteps | 96000 |\n", "| train/ | |\n", "| entropy_loss | -0.0557 |\n", "| explained_variance | -0.179 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -6.21e-05 |\n", "| value_loss | 6.77e-05 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 399 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19300 |\n", "| time_elapsed | 514 |\n", "| total_timesteps | 96500 |\n", "| train/ | |\n", "| entropy_loss | -1.42 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.000767 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19400 |\n", "| time_elapsed | 517 |\n", "| total_timesteps | 97000 |\n", "| train/ | |\n", "| entropy_loss | -1.39 |\n", "| explained_variance | 0.186 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19500 |\n", "| time_elapsed | 520 |\n", "| total_timesteps | 97500 |\n", "| train/ | |\n", "| entropy_loss | -1.5 |\n", "| explained_variance | 0.00668 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0228 |\n", "| value_loss | 0.000246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 404 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19600 |\n", "| time_elapsed | 522 |\n", "| total_timesteps | 98000 |\n", "| train/ | |\n", "| entropy_loss | -0.801 |\n", "| explained_variance | -0.0599 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00407 |\n", "| value_loss | 0.000186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 403 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19700 |\n", "| time_elapsed | 525 |\n", "| total_timesteps | 98500 |\n", "| train/ | |\n", "| entropy_loss | -0.978 |\n", "| explained_variance | 0.0505 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00808 |\n", "| value_loss | 6.03e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 397 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19800 |\n", "| time_elapsed | 527 |\n", "| total_timesteps | 99000 |\n", "| train/ | |\n", "| entropy_loss | -0.276 |\n", "| explained_variance | 0.0509 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0339 |\n", "| value_loss | 0.508 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 397 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 19900 |\n", "| time_elapsed | 530 |\n", "| total_timesteps | 99500 |\n", "| train/ | |\n", "| entropy_loss | -1.48 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0118 |\n", "| value_loss | 5.67e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 398 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20000 |\n", "| time_elapsed | 533 |\n", "| total_timesteps | 100000 |\n", "| train/ | |\n", "| entropy_loss | -1.35 |\n", "| explained_variance | -1.85 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0112 |\n", "| value_loss | 5.14e-05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20100 |\n", "| time_elapsed | 535 |\n", "| total_timesteps | 100500 |\n", "| train/ | |\n", "| entropy_loss | -1.58 |\n", "| explained_variance | -0.0531 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0216 |\n", "| value_loss | 0.000178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 395 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20200 |\n", "| time_elapsed | 538 |\n", "| total_timesteps | 101000 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | 0.372 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.00049 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 395 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20300 |\n", "| time_elapsed | 540 |\n", "| total_timesteps | 101500 |\n", "| train/ | |\n", "| entropy_loss | -1.59 |\n", "| explained_variance | 0.0317 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0315 |\n", "| value_loss | 0.000407 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 9.98 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20400 |\n", "| time_elapsed | 543 |\n", "| total_timesteps | 102000 |\n", "| train/ | |\n", "| entropy_loss | -1.41 |\n", "| explained_variance | -15.1 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.191 |\n", "| value_loss | 0.0168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 10 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20500 |\n", "| time_elapsed | 546 |\n", "| total_timesteps | 102500 |\n", "| train/ | |\n", "| entropy_loss | -1.56 |\n", "| explained_variance | 0.0045 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0349 |\n", "| value_loss | 0.000579 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 389 |\n", "| ep_rew_mean | 10 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20600 |\n", "| time_elapsed | 548 |\n", "| total_timesteps | 103000 |\n", "| train/ | |\n", "| entropy_loss | -1.49 |\n", "| explained_variance | -0.157 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0618 |\n", "| value_loss | 0.00154 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20700 |\n", "| time_elapsed | 551 |\n", "| total_timesteps | 103500 |\n", "| train/ | |\n", "| entropy_loss | -1.42 |\n", "| explained_variance | -140 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.000463 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20800 |\n", "| time_elapsed | 553 |\n", "| total_timesteps | 104000 |\n", "| train/ | |\n", "| entropy_loss | -1.57 |\n", "| explained_variance | 0.038 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.55 |\n", "| value_loss | 3.62 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 20900 |\n", "| time_elapsed | 556 |\n", "| total_timesteps | 104500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0709 |\n", "| value_loss | 0.00299 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21000 |\n", "| time_elapsed | 559 |\n", "| total_timesteps | 105000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0305 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21100 |\n", "| time_elapsed | 561 |\n", "| total_timesteps | 105500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0669 |\n", "| value_loss | 0.00251 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21200 |\n", "| time_elapsed | 564 |\n", "| total_timesteps | 106000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21300 |\n", "| time_elapsed | 566 |\n", "| total_timesteps | 106500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0309 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 389 |\n", "| ep_rew_mean | 10.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21400 |\n", "| time_elapsed | 569 |\n", "| total_timesteps | 107000 |\n", "| train/ | |\n", "| entropy_loss | -0.896 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.888 |\n", "| value_loss | 0.346 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 21500 |\n", "| time_elapsed | 571 |\n", "| total_timesteps | 107500 |\n", "| train/ | |\n", "| entropy_loss | -0.793 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.41 |\n", "| value_loss | 1.42 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 21600 |\n", "| time_elapsed | 574 |\n", "| total_timesteps | 108000 |\n", "| train/ | |\n", "| entropy_loss | -0.801 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 390 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 21700 |\n", "| time_elapsed | 576 |\n", "| total_timesteps | 108500 |\n", "| train/ | |\n", "| entropy_loss | -0.898 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.064 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 21800 |\n", "| time_elapsed | 579 |\n", "| total_timesteps | 109000 |\n", "| train/ | |\n", "| entropy_loss | -0.834 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0779 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 21900 |\n", "| time_elapsed | 582 |\n", "| total_timesteps | 109500 |\n", "| train/ | |\n", "| entropy_loss | -0.795 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0332 |\n", "| value_loss | 0.00155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22000 |\n", "| time_elapsed | 584 |\n", "| total_timesteps | 110000 |\n", "| train/ | |\n", "| entropy_loss | -0.766 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00861 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22100 |\n", "| time_elapsed | 587 |\n", "| total_timesteps | 110500 |\n", "| train/ | |\n", "| entropy_loss | -0.744 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00825 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22200 |\n", "| time_elapsed | 589 |\n", "| total_timesteps | 111000 |\n", "| train/ | |\n", "| entropy_loss | -0.573 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00621 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 393 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22300 |\n", "| time_elapsed | 592 |\n", "| total_timesteps | 111500 |\n", "| train/ | |\n", "| entropy_loss | -0.564 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00597 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 393 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22400 |\n", "| time_elapsed | 594 |\n", "| total_timesteps | 112000 |\n", "| train/ | |\n", "| entropy_loss | -0.618 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0243 |\n", "| value_loss | 0.00149 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22500 |\n", "| time_elapsed | 597 |\n", "| total_timesteps | 112500 |\n", "| train/ | |\n", "| entropy_loss | -0.672 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0137 |\n", "| value_loss | 0.00114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22600 |\n", "| time_elapsed | 600 |\n", "| total_timesteps | 113000 |\n", "| train/ | |\n", "| entropy_loss | -0.645 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00523 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22700 |\n", "| time_elapsed | 602 |\n", "| total_timesteps | 113500 |\n", "| train/ | |\n", "| entropy_loss | -0.571 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0189 |\n", "| value_loss | 0.000856 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22800 |\n", "| time_elapsed | 605 |\n", "| total_timesteps | 114000 |\n", "| train/ | |\n", "| entropy_loss | -0.472 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00246 |\n", "| value_loss | 0.000574 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 22900 |\n", "| time_elapsed | 607 |\n", "| total_timesteps | 114500 |\n", "| train/ | |\n", "| entropy_loss | -0.431 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0293 |\n", "| value_loss | 0.204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23000 |\n", "| time_elapsed | 610 |\n", "| total_timesteps | 115000 |\n", "| train/ | |\n", "| entropy_loss | -0.341 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00171 |\n", "| value_loss | 0.000656 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23100 |\n", "| time_elapsed | 613 |\n", "| total_timesteps | 115500 |\n", "| train/ | |\n", "| entropy_loss | -0.353 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00135 |\n", "| value_loss | 0.000371 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 392 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23200 |\n", "| time_elapsed | 615 |\n", "| total_timesteps | 116000 |\n", "| train/ | |\n", "| entropy_loss | -0.416 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00147 |\n", "| value_loss | 0.000281 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 391 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23300 |\n", "| time_elapsed | 618 |\n", "| total_timesteps | 116500 |\n", "| train/ | |\n", "| entropy_loss | -0.385 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00104 |\n", "| value_loss | 0.000169 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 393 |\n", "| ep_rew_mean | 10.3 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23400 |\n", "| time_elapsed | 620 |\n", "| total_timesteps | 117000 |\n", "| train/ | |\n", "| entropy_loss | -0.56 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00167 |\n", "| value_loss | 0.000156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 393 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23500 |\n", "| time_elapsed | 623 |\n", "| total_timesteps | 117500 |\n", "| train/ | |\n", "| entropy_loss | -0.528 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00197 |\n", "| value_loss | 0.000262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 393 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23600 |\n", "| time_elapsed | 626 |\n", "| total_timesteps | 118000 |\n", "| train/ | |\n", "| entropy_loss | -0.588 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00275 |\n", "| value_loss | 0.000376 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 394 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23700 |\n", "| time_elapsed | 628 |\n", "| total_timesteps | 118500 |\n", "| train/ | |\n", "| entropy_loss | -0.613 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.156 |\n", "| value_loss | 1.31 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 395 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23800 |\n", "| time_elapsed | 631 |\n", "| total_timesteps | 119000 |\n", "| train/ | |\n", "| entropy_loss | -0.602 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0165 |\n", "| value_loss | 0.000672 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 395 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 23900 |\n", "| time_elapsed | 633 |\n", "| total_timesteps | 119500 |\n", "| train/ | |\n", "| entropy_loss | -0.776 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00564 |\n", "| value_loss | 0.000692 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24000 |\n", "| time_elapsed | 636 |\n", "| total_timesteps | 120000 |\n", "| train/ | |\n", "| entropy_loss | -0.699 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0268 |\n", "| value_loss | 0.00115 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24100 |\n", "| time_elapsed | 639 |\n", "| total_timesteps | 120500 |\n", "| train/ | |\n", "| entropy_loss | -0.663 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0255 |\n", "| value_loss | 0.000885 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 10.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24200 |\n", "| time_elapsed | 641 |\n", "| total_timesteps | 121000 |\n", "| train/ | |\n", "| entropy_loss | -0.702 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00686 |\n", "| value_loss | 0.00136 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 395 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24300 |\n", "| time_elapsed | 644 |\n", "| total_timesteps | 121500 |\n", "| train/ | |\n", "| entropy_loss | -0.889 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.049 |\n", "| value_loss | 0.00122 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 10.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24400 |\n", "| time_elapsed | 646 |\n", "| total_timesteps | 122000 |\n", "| train/ | |\n", "| entropy_loss | -0.903 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00121 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 396 |\n", "| ep_rew_mean | 10.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24500 |\n", "| time_elapsed | 649 |\n", "| total_timesteps | 122500 |\n", "| train/ | |\n", "| entropy_loss | -0.975 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0242 |\n", "| value_loss | 0.00118 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 398 |\n", "| ep_rew_mean | 10.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24600 |\n", "| time_elapsed | 652 |\n", "| total_timesteps | 123000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.204 |\n", "| value_loss | 0.479 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 400 |\n", "| ep_rew_mean | 10.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24700 |\n", "| time_elapsed | 654 |\n", "| total_timesteps | 123500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.12 |\n", "| value_loss | 1.68 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 401 |\n", "| ep_rew_mean | 10.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24800 |\n", "| time_elapsed | 657 |\n", "| total_timesteps | 124000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0357 |\n", "| value_loss | 0.00145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 24900 |\n", "| time_elapsed | 659 |\n", "| total_timesteps | 124500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.508 |\n", "| value_loss | 0.529 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 402 |\n", "| ep_rew_mean | 11 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25000 |\n", "| time_elapsed | 662 |\n", "| total_timesteps | 125000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25100 |\n", "| time_elapsed | 664 |\n", "| total_timesteps | 125500 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.03 |\n", "| value_loss | 1.46 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 404 |\n", "| ep_rew_mean | 11.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25200 |\n", "| time_elapsed | 667 |\n", "| total_timesteps | 126000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0162 |\n", "| value_loss | 0.00155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 11.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25300 |\n", "| time_elapsed | 669 |\n", "| total_timesteps | 126500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0266 |\n", "| value_loss | 0.00147 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 405 |\n", "| ep_rew_mean | 11.3 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25400 |\n", "| time_elapsed | 672 |\n", "| total_timesteps | 127000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0344 |\n", "| value_loss | 0.00145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 407 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25500 |\n", "| time_elapsed | 675 |\n", "| total_timesteps | 127500 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0645 |\n", "| value_loss | 0.00147 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 409 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25600 |\n", "| time_elapsed | 677 |\n", "| total_timesteps | 128000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.0015 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 410 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25700 |\n", "| time_elapsed | 680 |\n", "| total_timesteps | 128500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0283 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 411 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25800 |\n", "| time_elapsed | 682 |\n", "| total_timesteps | 129000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0599 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 412 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 25900 |\n", "| time_elapsed | 685 |\n", "| total_timesteps | 129500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0236 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26000 |\n", "| time_elapsed | 688 |\n", "| total_timesteps | 130000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.022 |\n", "| value_loss | 0.00146 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 414 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26100 |\n", "| time_elapsed | 690 |\n", "| total_timesteps | 130500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 415 |\n", "| ep_rew_mean | 12.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26200 |\n", "| time_elapsed | 693 |\n", "| total_timesteps | 131000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.0016 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 416 |\n", "| ep_rew_mean | 12.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26300 |\n", "| time_elapsed | 695 |\n", "| total_timesteps | 131500 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 418 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26400 |\n", "| time_elapsed | 698 |\n", "| total_timesteps | 132000 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0207 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 421 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26500 |\n", "| time_elapsed | 701 |\n", "| total_timesteps | 132500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.0016 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 422 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26600 |\n", "| time_elapsed | 703 |\n", "| total_timesteps | 133000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0232 |\n", "| value_loss | 0.00152 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 424 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 26700 |\n", "| time_elapsed | 706 |\n", "| total_timesteps | 133500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 424 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 26800 |\n", "| time_elapsed | 708 |\n", "| total_timesteps | 134000 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0168 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 428 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 26900 |\n", "| time_elapsed | 711 |\n", "| total_timesteps | 134500 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.121 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27000 |\n", "| time_elapsed | 714 |\n", "| total_timesteps | 135000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0524 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 430 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27100 |\n", "| time_elapsed | 716 |\n", "| total_timesteps | 135500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.61 |\n", "| value_loss | 0.893 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 431 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27200 |\n", "| time_elapsed | 719 |\n", "| total_timesteps | 136000 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.706 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 433 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27300 |\n", "| time_elapsed | 722 |\n", "| total_timesteps | 136500 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 433 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27400 |\n", "| time_elapsed | 724 |\n", "| total_timesteps | 137000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.643 |\n", "| value_loss | 2.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 435 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27500 |\n", "| time_elapsed | 727 |\n", "| total_timesteps | 137500 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00167 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 436 |\n", "| ep_rew_mean | 14.2 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27600 |\n", "| time_elapsed | 729 |\n", "| total_timesteps | 138000 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0265 |\n", "| value_loss | 0.00194 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 437 |\n", "| ep_rew_mean | 14.3 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27700 |\n", "| time_elapsed | 732 |\n", "| total_timesteps | 138500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.077 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 439 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27800 |\n", "| time_elapsed | 735 |\n", "| total_timesteps | 139000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0209 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 440 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 27900 |\n", "| time_elapsed | 737 |\n", "| total_timesteps | 139500 |\n", "| train/ | |\n", "| entropy_loss | -0.999 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 442 |\n", "| ep_rew_mean | 14.7 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28000 |\n", "| time_elapsed | 740 |\n", "| total_timesteps | 140000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 443 |\n", "| ep_rew_mean | 14.8 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28100 |\n", "| time_elapsed | 742 |\n", "| total_timesteps | 140500 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.0016 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 443 |\n", "| ep_rew_mean | 14.7 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28200 |\n", "| time_elapsed | 745 |\n", "| total_timesteps | 141000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0296 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 443 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28300 |\n", "| time_elapsed | 747 |\n", "| total_timesteps | 141500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0348 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 441 |\n", "| ep_rew_mean | 14.2 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28400 |\n", "| time_elapsed | 750 |\n", "| total_timesteps | 142000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 445 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28500 |\n", "| time_elapsed | 753 |\n", "| total_timesteps | 142500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.0014 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 446 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28600 |\n", "| time_elapsed | 755 |\n", "| total_timesteps | 143000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 448 |\n", "| ep_rew_mean | 14.8 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28700 |\n", "| time_elapsed | 758 |\n", "| total_timesteps | 143500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0508 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 451 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28800 |\n", "| time_elapsed | 760 |\n", "| total_timesteps | 144000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 452 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 28900 |\n", "| time_elapsed | 763 |\n", "| total_timesteps | 144500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 452 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29000 |\n", "| time_elapsed | 766 |\n", "| total_timesteps | 145000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0687 |\n", "| value_loss | 0.00176 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 453 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29100 |\n", "| time_elapsed | 768 |\n", "| total_timesteps | 145500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 456 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29200 |\n", "| time_elapsed | 771 |\n", "| total_timesteps | 146000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.00154 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 457 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29300 |\n", "| time_elapsed | 773 |\n", "| total_timesteps | 146500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0594 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 459 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29400 |\n", "| time_elapsed | 776 |\n", "| total_timesteps | 147000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.111 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 460 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29500 |\n", "| time_elapsed | 779 |\n", "| total_timesteps | 147500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 461 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29600 |\n", "| time_elapsed | 781 |\n", "| total_timesteps | 148000 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.044 |\n", "| value_loss | 0.176 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 463 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29700 |\n", "| time_elapsed | 784 |\n", "| total_timesteps | 148500 |\n", "| train/ | |\n", "| entropy_loss | -0.985 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0149 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 463 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29800 |\n", "| time_elapsed | 786 |\n", "| total_timesteps | 149000 |\n", "| train/ | |\n", "| entropy_loss | -0.907 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 189 |\n", "| iterations | 29900 |\n", "| time_elapsed | 789 |\n", "| total_timesteps | 149500 |\n", "| train/ | |\n", "| entropy_loss | -0.862 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0764 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "Eval num_timesteps=150000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 150000 |\n", "| train/ | |\n", "| entropy_loss | -0.914 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.339 |\n", "| value_loss | 1.33 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30000 |\n", "| time_elapsed | 802 |\n", "| total_timesteps | 150000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30100 |\n", "| time_elapsed | 805 |\n", "| total_timesteps | 150500 |\n", "| train/ | |\n", "| entropy_loss | -0.705 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00843 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30200 |\n", "| time_elapsed | 808 |\n", "| total_timesteps | 151000 |\n", "| train/ | |\n", "| entropy_loss | -0.734 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0155 |\n", "| value_loss | 0.00187 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30300 |\n", "| time_elapsed | 810 |\n", "| total_timesteps | 151500 |\n", "| train/ | |\n", "| entropy_loss | -0.852 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 464 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30400 |\n", "| time_elapsed | 813 |\n", "| total_timesteps | 152000 |\n", "| train/ | |\n", "| entropy_loss | -0.852 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00143 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 465 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30500 |\n", "| time_elapsed | 815 |\n", "| total_timesteps | 152500 |\n", "| train/ | |\n", "| entropy_loss | -0.845 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 466 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30600 |\n", "| time_elapsed | 818 |\n", "| total_timesteps | 153000 |\n", "| train/ | |\n", "| entropy_loss | -0.728 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0405 |\n", "| value_loss | 0.00159 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 468 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30700 |\n", "| time_elapsed | 821 |\n", "| total_timesteps | 153500 |\n", "| train/ | |\n", "| entropy_loss | -0.806 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.12 |\n", "| value_loss | 0.898 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 469 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30800 |\n", "| time_elapsed | 823 |\n", "| total_timesteps | 154000 |\n", "| train/ | |\n", "| entropy_loss | -0.761 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0394 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 469 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 30900 |\n", "| time_elapsed | 826 |\n", "| total_timesteps | 154500 |\n", "| train/ | |\n", "| entropy_loss | -0.796 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0308 |\n", "| value_loss | 0.00159 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 470 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 31000 |\n", "| time_elapsed | 829 |\n", "| total_timesteps | 155000 |\n", "| train/ | |\n", "| entropy_loss | -0.882 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0146 |\n", "| value_loss | 0.00131 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 471 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 31100 |\n", "| time_elapsed | 831 |\n", "| total_timesteps | 155500 |\n", "| train/ | |\n", "| entropy_loss | -0.823 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0253 |\n", "| value_loss | 0.00143 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 472 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 31200 |\n", "| time_elapsed | 834 |\n", "| total_timesteps | 156000 |\n", "| train/ | |\n", "| entropy_loss | -0.769 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.088 |\n", "| value_loss | 0.358 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 471 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31300 |\n", "| time_elapsed | 836 |\n", "| total_timesteps | 156500 |\n", "| train/ | |\n", "| entropy_loss | -0.808 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00138 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31400 |\n", "| time_elapsed | 839 |\n", "| total_timesteps | 157000 |\n", "| train/ | |\n", "| entropy_loss | -0.708 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0202 |\n", "| value_loss | 0.176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31500 |\n", "| time_elapsed | 842 |\n", "| total_timesteps | 157500 |\n", "| train/ | |\n", "| entropy_loss | -0.697 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00739 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31600 |\n", "| time_elapsed | 844 |\n", "| total_timesteps | 158000 |\n", "| train/ | |\n", "| entropy_loss | -0.618 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00674 |\n", "| value_loss | 0.00186 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31700 |\n", "| time_elapsed | 847 |\n", "| total_timesteps | 158500 |\n", "| train/ | |\n", "| entropy_loss | -0.734 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0081 |\n", "| value_loss | 0.00158 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31800 |\n", "| time_elapsed | 849 |\n", "| total_timesteps | 159000 |\n", "| train/ | |\n", "| entropy_loss | -0.659 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.013 |\n", "| value_loss | 0.00155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 31900 |\n", "| time_elapsed | 852 |\n", "| total_timesteps | 159500 |\n", "| train/ | |\n", "| entropy_loss | -0.674 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32000 |\n", "| time_elapsed | 855 |\n", "| total_timesteps | 160000 |\n", "| train/ | |\n", "| entropy_loss | -0.726 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.167 |\n", "| value_loss | 0.718 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32100 |\n", "| time_elapsed | 857 |\n", "| total_timesteps | 160500 |\n", "| train/ | |\n", "| entropy_loss | -0.685 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0651 |\n", "| value_loss | 0.00166 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32200 |\n", "| time_elapsed | 860 |\n", "| total_timesteps | 161000 |\n", "| train/ | |\n", "| entropy_loss | -0.723 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00765 |\n", "| value_loss | 0.00148 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32300 |\n", "| time_elapsed | 862 |\n", "| total_timesteps | 161500 |\n", "| train/ | |\n", "| entropy_loss | -0.76 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0635 |\n", "| value_loss | 0.00152 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32400 |\n", "| time_elapsed | 865 |\n", "| total_timesteps | 162000 |\n", "| train/ | |\n", "| entropy_loss | -0.791 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0248 |\n", "| value_loss | 0.00144 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32500 |\n", "| time_elapsed | 868 |\n", "| total_timesteps | 162500 |\n", "| train/ | |\n", "| entropy_loss | -0.796 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0306 |\n", "| value_loss | 0.00147 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 478 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32600 |\n", "| time_elapsed | 870 |\n", "| total_timesteps | 163000 |\n", "| train/ | |\n", "| entropy_loss | -0.743 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0311 |\n", "| value_loss | 0.00129 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 479 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32700 |\n", "| time_elapsed | 873 |\n", "| total_timesteps | 163500 |\n", "| train/ | |\n", "| entropy_loss | -0.663 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32800 |\n", "| time_elapsed | 875 |\n", "| total_timesteps | 164000 |\n", "| train/ | |\n", "| entropy_loss | -0.649 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.699 |\n", "| value_loss | 0.892 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 32900 |\n", "| time_elapsed | 878 |\n", "| total_timesteps | 164500 |\n", "| train/ | |\n", "| entropy_loss | -0.588 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0061 |\n", "| value_loss | 0.00173 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33000 |\n", "| time_elapsed | 881 |\n", "| total_timesteps | 165000 |\n", "| train/ | |\n", "| entropy_loss | -0.619 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0338 |\n", "| value_loss | 0.00157 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 16.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33100 |\n", "| time_elapsed | 883 |\n", "| total_timesteps | 165500 |\n", "| train/ | |\n", "| entropy_loss | -0.723 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0326 |\n", "| value_loss | 0.00129 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33200 |\n", "| time_elapsed | 886 |\n", "| total_timesteps | 166000 |\n", "| train/ | |\n", "| entropy_loss | -0.767 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.78 |\n", "| value_loss | 1.84 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33300 |\n", "| time_elapsed | 889 |\n", "| total_timesteps | 166500 |\n", "| train/ | |\n", "| entropy_loss | -0.784 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00936 |\n", "| value_loss | 0.00165 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33400 |\n", "| time_elapsed | 891 |\n", "| total_timesteps | 167000 |\n", "| train/ | |\n", "| entropy_loss | -0.833 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00153 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33500 |\n", "| time_elapsed | 894 |\n", "| total_timesteps | 167500 |\n", "| train/ | |\n", "| entropy_loss | -0.879 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0247 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33600 |\n", "| time_elapsed | 896 |\n", "| total_timesteps | 168000 |\n", "| train/ | |\n", "| entropy_loss | -0.783 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.149 |\n", "| value_loss | 0.619 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33700 |\n", "| time_elapsed | 899 |\n", "| total_timesteps | 168500 |\n", "| train/ | |\n", "| entropy_loss | -0.794 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00954 |\n", "| value_loss | 0.00162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33800 |\n", "| time_elapsed | 902 |\n", "| total_timesteps | 169000 |\n", "| train/ | |\n", "| entropy_loss | -0.792 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00861 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 33900 |\n", "| time_elapsed | 904 |\n", "| total_timesteps | 169500 |\n", "| train/ | |\n", "| entropy_loss | -0.888 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0092 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34000 |\n", "| time_elapsed | 907 |\n", "| total_timesteps | 170000 |\n", "| train/ | |\n", "| entropy_loss | -0.757 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.013 |\n", "| value_loss | 0.00138 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34100 |\n", "| time_elapsed | 909 |\n", "| total_timesteps | 170500 |\n", "| train/ | |\n", "| entropy_loss | -0.796 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.025 |\n", "| value_loss | 0.00112 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34200 |\n", "| time_elapsed | 912 |\n", "| total_timesteps | 171000 |\n", "| train/ | |\n", "| entropy_loss | -0.721 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0253 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34300 |\n", "| time_elapsed | 915 |\n", "| total_timesteps | 171500 |\n", "| train/ | |\n", "| entropy_loss | -0.642 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00622 |\n", "| value_loss | 0.00136 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34400 |\n", "| time_elapsed | 917 |\n", "| total_timesteps | 172000 |\n", "| train/ | |\n", "| entropy_loss | -0.629 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0211 |\n", "| value_loss | 0.00124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34500 |\n", "| time_elapsed | 920 |\n", "| total_timesteps | 172500 |\n", "| train/ | |\n", "| entropy_loss | -0.649 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0191 |\n", "| value_loss | 0.00124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34600 |\n", "| time_elapsed | 922 |\n", "| total_timesteps | 173000 |\n", "| train/ | |\n", "| entropy_loss | -0.675 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34700 |\n", "| time_elapsed | 925 |\n", "| total_timesteps | 173500 |\n", "| train/ | |\n", "| entropy_loss | -0.551 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00486 |\n", "| value_loss | 0.00129 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34800 |\n", "| time_elapsed | 928 |\n", "| total_timesteps | 174000 |\n", "| train/ | |\n", "| entropy_loss | -0.503 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00456 |\n", "| value_loss | 0.0015 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 34900 |\n", "| time_elapsed | 930 |\n", "| total_timesteps | 174500 |\n", "| train/ | |\n", "| entropy_loss | -0.692 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0301 |\n", "| value_loss | 0.00114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 16.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35000 |\n", "| time_elapsed | 933 |\n", "| total_timesteps | 175000 |\n", "| train/ | |\n", "| entropy_loss | -0.74 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.00102 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35100 |\n", "| time_elapsed | 935 |\n", "| total_timesteps | 175500 |\n", "| train/ | |\n", "| entropy_loss | -0.738 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0076 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35200 |\n", "| time_elapsed | 938 |\n", "| total_timesteps | 176000 |\n", "| train/ | |\n", "| entropy_loss | -0.74 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0506 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35300 |\n", "| time_elapsed | 940 |\n", "| total_timesteps | 176500 |\n", "| train/ | |\n", "| entropy_loss | -0.613 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0567 |\n", "| value_loss | 0.000954 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 16.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35400 |\n", "| time_elapsed | 943 |\n", "| total_timesteps | 177000 |\n", "| train/ | |\n", "| entropy_loss | -0.746 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00655 |\n", "| value_loss | 0.000916 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35500 |\n", "| time_elapsed | 946 |\n", "| total_timesteps | 177500 |\n", "| train/ | |\n", "| entropy_loss | -0.648 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00535 |\n", "| value_loss | 0.000948 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35600 |\n", "| time_elapsed | 948 |\n", "| total_timesteps | 178000 |\n", "| train/ | |\n", "| entropy_loss | -0.626 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.173 |\n", "| value_loss | 0.903 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35700 |\n", "| time_elapsed | 951 |\n", "| total_timesteps | 178500 |\n", "| train/ | |\n", "| entropy_loss | -0.617 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0226 |\n", "| value_loss | 0.000964 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35800 |\n", "| time_elapsed | 953 |\n", "| total_timesteps | 179000 |\n", "| train/ | |\n", "| entropy_loss | -0.536 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0108 |\n", "| value_loss | 0.182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 35900 |\n", "| time_elapsed | 956 |\n", "| total_timesteps | 179500 |\n", "| train/ | |\n", "| entropy_loss | -0.647 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.028 |\n", "| value_loss | 0.00106 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36000 |\n", "| time_elapsed | 959 |\n", "| total_timesteps | 180000 |\n", "| train/ | |\n", "| entropy_loss | -0.619 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0102 |\n", "| value_loss | 0.000975 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36100 |\n", "| time_elapsed | 961 |\n", "| total_timesteps | 180500 |\n", "| train/ | |\n", "| entropy_loss | -0.669 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00571 |\n", "| value_loss | 0.000986 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36200 |\n", "| time_elapsed | 964 |\n", "| total_timesteps | 181000 |\n", "| train/ | |\n", "| entropy_loss | -0.683 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0065 |\n", "| value_loss | 0.00119 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36300 |\n", "| time_elapsed | 966 |\n", "| total_timesteps | 181500 |\n", "| train/ | |\n", "| entropy_loss | -0.608 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00507 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 15.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36400 |\n", "| time_elapsed | 969 |\n", "| total_timesteps | 182000 |\n", "| train/ | |\n", "| entropy_loss | -0.635 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00567 |\n", "| value_loss | 0.00114 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 15.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36500 |\n", "| time_elapsed | 971 |\n", "| total_timesteps | 182500 |\n", "| train/ | |\n", "| entropy_loss | -0.656 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0057 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36600 |\n", "| time_elapsed | 974 |\n", "| total_timesteps | 183000 |\n", "| train/ | |\n", "| entropy_loss | -0.656 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0242 |\n", "| value_loss | 0.183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36700 |\n", "| time_elapsed | 977 |\n", "| total_timesteps | 183500 |\n", "| train/ | |\n", "| entropy_loss | -0.642 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0177 |\n", "| value_loss | 0.000761 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36800 |\n", "| time_elapsed | 979 |\n", "| total_timesteps | 184000 |\n", "| train/ | |\n", "| entropy_loss | -0.647 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0182 |\n", "| value_loss | 0.000964 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 36900 |\n", "| time_elapsed | 982 |\n", "| total_timesteps | 184500 |\n", "| train/ | |\n", "| entropy_loss | -0.609 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00454 |\n", "| value_loss | 0.000826 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37000 |\n", "| time_elapsed | 985 |\n", "| total_timesteps | 185000 |\n", "| train/ | |\n", "| entropy_loss | -0.679 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00519 |\n", "| value_loss | 0.000777 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37100 |\n", "| time_elapsed | 987 |\n", "| total_timesteps | 185500 |\n", "| train/ | |\n", "| entropy_loss | -0.647 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0294 |\n", "| value_loss | 0.000911 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37200 |\n", "| time_elapsed | 990 |\n", "| total_timesteps | 186000 |\n", "| train/ | |\n", "| entropy_loss | -0.628 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00574 |\n", "| value_loss | 0.00119 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37300 |\n", "| time_elapsed | 992 |\n", "| total_timesteps | 186500 |\n", "| train/ | |\n", "| entropy_loss | -0.779 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.04 |\n", "| value_loss | 0.91 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37400 |\n", "| time_elapsed | 995 |\n", "| total_timesteps | 187000 |\n", "| train/ | |\n", "| entropy_loss | -0.74 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00783 |\n", "| value_loss | 0.00128 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37500 |\n", "| time_elapsed | 998 |\n", "| total_timesteps | 187500 |\n", "| train/ | |\n", "| entropy_loss | -0.809 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0231 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 479 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37600 |\n", "| time_elapsed | 1000 |\n", "| total_timesteps | 188000 |\n", "| train/ | |\n", "| entropy_loss | -0.807 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00126 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37700 |\n", "| time_elapsed | 1003 |\n", "| total_timesteps | 188500 |\n", "| train/ | |\n", "| entropy_loss | -0.691 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0123 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37800 |\n", "| time_elapsed | 1005 |\n", "| total_timesteps | 189000 |\n", "| train/ | |\n", "| entropy_loss | -0.805 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00112 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 37900 |\n", "| time_elapsed | 1008 |\n", "| total_timesteps | 189500 |\n", "| train/ | |\n", "| entropy_loss | -0.8 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 480 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38000 |\n", "| time_elapsed | 1011 |\n", "| total_timesteps | 190000 |\n", "| train/ | |\n", "| entropy_loss | -0.878 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00877 |\n", "| value_loss | 0.000918 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38100 |\n", "| time_elapsed | 1013 |\n", "| total_timesteps | 190500 |\n", "| train/ | |\n", "| entropy_loss | -0.975 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0439 |\n", "| value_loss | 0.00091 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 478 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38200 |\n", "| time_elapsed | 1016 |\n", "| total_timesteps | 191000 |\n", "| train/ | |\n", "| entropy_loss | -0.943 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0645 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 14.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38300 |\n", "| time_elapsed | 1019 |\n", "| total_timesteps | 191500 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0544 |\n", "| value_loss | 0.000975 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 14.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38400 |\n", "| time_elapsed | 1021 |\n", "| total_timesteps | 192000 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.000858 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 14.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38500 |\n", "| time_elapsed | 1024 |\n", "| total_timesteps | 192500 |\n", "| train/ | |\n", "| entropy_loss | -1.05 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0293 |\n", "| value_loss | 0.000709 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 14.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38600 |\n", "| time_elapsed | 1026 |\n", "| total_timesteps | 193000 |\n", "| train/ | |\n", "| entropy_loss | -0.999 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0331 |\n", "| value_loss | 0.000874 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 14 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38700 |\n", "| time_elapsed | 1029 |\n", "| total_timesteps | 193500 |\n", "| train/ | |\n", "| entropy_loss | -0.999 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.025 |\n", "| value_loss | 0.000889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38800 |\n", "| time_elapsed | 1032 |\n", "| total_timesteps | 194000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0189 |\n", "| value_loss | 0.000796 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 38900 |\n", "| time_elapsed | 1034 |\n", "| total_timesteps | 194500 |\n", "| train/ | |\n", "| entropy_loss | -1.04 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.000771 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 39000 |\n", "| time_elapsed | 1037 |\n", "| total_timesteps | 195000 |\n", "| train/ | |\n", "| entropy_loss | -1.04 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0126 |\n", "| value_loss | 0.000677 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 39100 |\n", "| time_elapsed | 1039 |\n", "| total_timesteps | 195500 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0298 |\n", "| value_loss | 0.000836 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 473 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39200 |\n", "| time_elapsed | 1042 |\n", "| total_timesteps | 196000 |\n", "| train/ | |\n", "| entropy_loss | -1.05 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.71 |\n", "| value_loss | 1.31 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 474 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39300 |\n", "| time_elapsed | 1045 |\n", "| total_timesteps | 196500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0276 |\n", "| value_loss | 0.000822 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39400 |\n", "| time_elapsed | 1047 |\n", "| total_timesteps | 197000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0206 |\n", "| value_loss | 0.000894 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39500 |\n", "| time_elapsed | 1050 |\n", "| total_timesteps | 197500 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.447 |\n", "| value_loss | 0.36 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39600 |\n", "| time_elapsed | 1052 |\n", "| total_timesteps | 198000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0346 |\n", "| value_loss | 0.00142 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39700 |\n", "| time_elapsed | 1055 |\n", "| total_timesteps | 198500 |\n", "| train/ | |\n", "| entropy_loss | -0.988 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0339 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39800 |\n", "| time_elapsed | 1057 |\n", "| total_timesteps | 199000 |\n", "| train/ | |\n", "| entropy_loss | -0.977 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0153 |\n", "| value_loss | 0.00114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 39900 |\n", "| time_elapsed | 1060 |\n", "| total_timesteps | 199500 |\n", "| train/ | |\n", "| entropy_loss | -0.971 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.000865 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40000 |\n", "| time_elapsed | 1063 |\n", "| total_timesteps | 200000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0108 |\n", "| value_loss | 0.000782 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40100 |\n", "| time_elapsed | 1065 |\n", "| total_timesteps | 200500 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0178 |\n", "| value_loss | 0.000899 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40200 |\n", "| time_elapsed | 1068 |\n", "| total_timesteps | 201000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0157 |\n", "| value_loss | 0.000852 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40300 |\n", "| time_elapsed | 1070 |\n", "| total_timesteps | 201500 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0177 |\n", "| value_loss | 0.000881 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40400 |\n", "| time_elapsed | 1073 |\n", "| total_timesteps | 202000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.000727 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40500 |\n", "| time_elapsed | 1076 |\n", "| total_timesteps | 202500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0215 |\n", "| value_loss | 0.000746 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40600 |\n", "| time_elapsed | 1078 |\n", "| total_timesteps | 203000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.0009 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40700 |\n", "| time_elapsed | 1081 |\n", "| total_timesteps | 203500 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0293 |\n", "| value_loss | 0.000879 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40800 |\n", "| time_elapsed | 1083 |\n", "| total_timesteps | 204000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0212 |\n", "| value_loss | 0.00101 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 40900 |\n", "| time_elapsed | 1086 |\n", "| total_timesteps | 204500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0251 |\n", "| value_loss | 0.000904 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41000 |\n", "| time_elapsed | 1088 |\n", "| total_timesteps | 205000 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0313 |\n", "| value_loss | 0.000846 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 475 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41100 |\n", "| time_elapsed | 1091 |\n", "| total_timesteps | 205500 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0324 |\n", "| value_loss | 0.000841 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41200 |\n", "| time_elapsed | 1094 |\n", "| total_timesteps | 206000 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0137 |\n", "| value_loss | 0.000818 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 476 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41300 |\n", "| time_elapsed | 1096 |\n", "| total_timesteps | 206500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0366 |\n", "| value_loss | 0.00071 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41400 |\n", "| time_elapsed | 1099 |\n", "| total_timesteps | 207000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0198 |\n", "| value_loss | 0.000722 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 477 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41500 |\n", "| time_elapsed | 1102 |\n", "| total_timesteps | 207500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.0007 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41600 |\n", "| time_elapsed | 1104 |\n", "| total_timesteps | 208000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0356 |\n", "| value_loss | 0.000623 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41700 |\n", "| time_elapsed | 1107 |\n", "| total_timesteps | 208500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.398 |\n", "| value_loss | 0.369 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41800 |\n", "| time_elapsed | 1109 |\n", "| total_timesteps | 209000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0274 |\n", "| value_loss | 0.00054 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 482 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 41900 |\n", "| time_elapsed | 1112 |\n", "| total_timesteps | 209500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.476 |\n", "| value_loss | 0.369 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42000 |\n", "| time_elapsed | 1115 |\n", "| total_timesteps | 210000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0925 |\n", "| value_loss | 0.183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 481 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42100 |\n", "| time_elapsed | 1117 |\n", "| total_timesteps | 210500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0222 |\n", "| value_loss | 0.000733 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42200 |\n", "| time_elapsed | 1120 |\n", "| total_timesteps | 211000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0445 |\n", "| value_loss | 0.00074 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42300 |\n", "| time_elapsed | 1122 |\n", "| total_timesteps | 211500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.018 |\n", "| value_loss | 0.000665 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42400 |\n", "| time_elapsed | 1125 |\n", "| total_timesteps | 212000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00079 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42500 |\n", "| time_elapsed | 1128 |\n", "| total_timesteps | 212500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.029 |\n", "| value_loss | 0.000702 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42600 |\n", "| time_elapsed | 1130 |\n", "| total_timesteps | 213000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0212 |\n", "| value_loss | 0.0007 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42700 |\n", "| time_elapsed | 1133 |\n", "| total_timesteps | 213500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.45 |\n", "| value_loss | 2.63 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42800 |\n", "| time_elapsed | 1135 |\n", "| total_timesteps | 214000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.929 |\n", "| value_loss | 0.557 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 42900 |\n", "| time_elapsed | 1138 |\n", "| total_timesteps | 214500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0207 |\n", "| value_loss | 0.000398 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43000 |\n", "| time_elapsed | 1141 |\n", "| total_timesteps | 215000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0258 |\n", "| value_loss | 0.000498 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43100 |\n", "| time_elapsed | 1143 |\n", "| total_timesteps | 215500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0261 |\n", "| value_loss | 0.00062 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43200 |\n", "| time_elapsed | 1146 |\n", "| total_timesteps | 216000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0281 |\n", "| value_loss | 0.000579 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43300 |\n", "| time_elapsed | 1148 |\n", "| total_timesteps | 216500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0162 |\n", "| value_loss | 0.000739 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43400 |\n", "| time_elapsed | 1151 |\n", "| total_timesteps | 217000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00076 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43500 |\n", "| time_elapsed | 1153 |\n", "| total_timesteps | 217500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0293 |\n", "| value_loss | 0.000882 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43600 |\n", "| time_elapsed | 1156 |\n", "| total_timesteps | 218000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0284 |\n", "| value_loss | 0.000809 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43700 |\n", "| time_elapsed | 1159 |\n", "| total_timesteps | 218500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.617 |\n", "| value_loss | 0.728 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43800 |\n", "| time_elapsed | 1161 |\n", "| total_timesteps | 219000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00101 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 43900 |\n", "| time_elapsed | 1164 |\n", "| total_timesteps | 219500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.024 |\n", "| value_loss | 0.000866 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44000 |\n", "| time_elapsed | 1166 |\n", "| total_timesteps | 220000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00101 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44100 |\n", "| time_elapsed | 1169 |\n", "| total_timesteps | 220500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.000971 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44200 |\n", "| time_elapsed | 1172 |\n", "| total_timesteps | 221000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0271 |\n", "| value_loss | 0.00113 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44300 |\n", "| time_elapsed | 1174 |\n", "| total_timesteps | 221500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00121 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44400 |\n", "| time_elapsed | 1177 |\n", "| total_timesteps | 222000 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00139 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44500 |\n", "| time_elapsed | 1179 |\n", "| total_timesteps | 222500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0278 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44600 |\n", "| time_elapsed | 1182 |\n", "| total_timesteps | 223000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0307 |\n", "| value_loss | 0.0013 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44700 |\n", "| time_elapsed | 1184 |\n", "| total_timesteps | 223500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0321 |\n", "| value_loss | 0.00116 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44800 |\n", "| time_elapsed | 1187 |\n", "| total_timesteps | 224000 |\n", "| train/ | |\n", "| entropy_loss | -1.04 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0709 |\n", "| value_loss | 0.179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 44900 |\n", "| time_elapsed | 1190 |\n", "| total_timesteps | 224500 |\n", "| train/ | |\n", "| entropy_loss | -0.968 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0271 |\n", "| value_loss | 0.00162 |\n", "------------------------------------\n", "Eval num_timesteps=225000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 225000 |\n", "| train/ | |\n", "| entropy_loss | -0.932 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0332 |\n", "| value_loss | 0.00157 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 45000 |\n", "| time_elapsed | 1203 |\n", "| total_timesteps | 225000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 45100 |\n", "| time_elapsed | 1206 |\n", "| total_timesteps | 225500 |\n", "| train/ | |\n", "| entropy_loss | -0.862 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00142 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 45200 |\n", "| time_elapsed | 1208 |\n", "| total_timesteps | 226000 |\n", "| train/ | |\n", "| entropy_loss | -0.888 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.693 |\n", "| value_loss | 0.36 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 45300 |\n", "| time_elapsed | 1211 |\n", "| total_timesteps | 226500 |\n", "| train/ | |\n", "| entropy_loss | -0.909 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0151 |\n", "| value_loss | 0.000935 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45400 |\n", "| time_elapsed | 1213 |\n", "| total_timesteps | 227000 |\n", "| train/ | |\n", "| entropy_loss | -0.944 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0129 |\n", "| value_loss | 0.000921 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45500 |\n", "| time_elapsed | 1216 |\n", "| total_timesteps | 227500 |\n", "| train/ | |\n", "| entropy_loss | -0.953 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0273 |\n", "| value_loss | 0.000919 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45600 |\n", "| time_elapsed | 1219 |\n", "| total_timesteps | 228000 |\n", "| train/ | |\n", "| entropy_loss | -0.911 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00963 |\n", "| value_loss | 0.000906 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45700 |\n", "| time_elapsed | 1221 |\n", "| total_timesteps | 228500 |\n", "| train/ | |\n", "| entropy_loss | -0.938 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0187 |\n", "| value_loss | 0.000762 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45800 |\n", "| time_elapsed | 1224 |\n", "| total_timesteps | 229000 |\n", "| train/ | |\n", "| entropy_loss | -0.911 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0214 |\n", "| value_loss | 0.000961 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 45900 |\n", "| time_elapsed | 1226 |\n", "| total_timesteps | 229500 |\n", "| train/ | |\n", "| entropy_loss | -0.95 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.000849 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46000 |\n", "| time_elapsed | 1229 |\n", "| total_timesteps | 230000 |\n", "| train/ | |\n", "| entropy_loss | -0.956 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.027 |\n", "| value_loss | 0.000805 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46100 |\n", "| time_elapsed | 1232 |\n", "| total_timesteps | 230500 |\n", "| train/ | |\n", "| entropy_loss | -0.975 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0217 |\n", "| value_loss | 0.000834 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46200 |\n", "| time_elapsed | 1234 |\n", "| total_timesteps | 231000 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.018 |\n", "| value_loss | 0.00068 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46300 |\n", "| time_elapsed | 1237 |\n", "| total_timesteps | 231500 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.998 |\n", "| value_loss | 0.549 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46400 |\n", "| time_elapsed | 1239 |\n", "| total_timesteps | 232000 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.000808 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46500 |\n", "| time_elapsed | 1242 |\n", "| total_timesteps | 232500 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.015 |\n", "| value_loss | 0.000767 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46600 |\n", "| time_elapsed | 1245 |\n", "| total_timesteps | 233000 |\n", "| train/ | |\n", "| entropy_loss | -0.978 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.62 |\n", "| value_loss | 3.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46700 |\n", "| time_elapsed | 1247 |\n", "| total_timesteps | 233500 |\n", "| train/ | |\n", "| entropy_loss | -0.928 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.000853 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46800 |\n", "| time_elapsed | 1250 |\n", "| total_timesteps | 234000 |\n", "| train/ | |\n", "| entropy_loss | -0.949 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0174 |\n", "| value_loss | 0.000887 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 46900 |\n", "| time_elapsed | 1252 |\n", "| total_timesteps | 234500 |\n", "| train/ | |\n", "| entropy_loss | -0.918 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.000762 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47000 |\n", "| time_elapsed | 1255 |\n", "| total_timesteps | 235000 |\n", "| train/ | |\n", "| entropy_loss | -0.963 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0313 |\n", "| value_loss | 0.000815 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47100 |\n", "| time_elapsed | 1258 |\n", "| total_timesteps | 235500 |\n", "| train/ | |\n", "| entropy_loss | -0.936 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0306 |\n", "| value_loss | 0.000837 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47200 |\n", "| time_elapsed | 1260 |\n", "| total_timesteps | 236000 |\n", "| train/ | |\n", "| entropy_loss | -0.959 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.012 |\n", "| value_loss | 0.000744 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47300 |\n", "| time_elapsed | 1263 |\n", "| total_timesteps | 236500 |\n", "| train/ | |\n", "| entropy_loss | -0.993 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.000636 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47400 |\n", "| time_elapsed | 1265 |\n", "| total_timesteps | 237000 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0238 |\n", "| value_loss | 0.000578 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47500 |\n", "| time_elapsed | 1268 |\n", "| total_timesteps | 237500 |\n", "| train/ | |\n", "| entropy_loss | -0.915 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.000851 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47600 |\n", "| time_elapsed | 1271 |\n", "| total_timesteps | 238000 |\n", "| train/ | |\n", "| entropy_loss | -0.98 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0149 |\n", "| value_loss | 0.000831 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47700 |\n", "| time_elapsed | 1273 |\n", "| total_timesteps | 238500 |\n", "| train/ | |\n", "| entropy_loss | -0.941 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0113 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47800 |\n", "| time_elapsed | 1276 |\n", "| total_timesteps | 239000 |\n", "| train/ | |\n", "| entropy_loss | -0.904 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0129 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 47900 |\n", "| time_elapsed | 1278 |\n", "| total_timesteps | 239500 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0308 |\n", "| value_loss | 0.000934 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48000 |\n", "| time_elapsed | 1281 |\n", "| total_timesteps | 240000 |\n", "| train/ | |\n", "| entropy_loss | -0.918 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0298 |\n", "| value_loss | 0.00106 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48100 |\n", "| time_elapsed | 1284 |\n", "| total_timesteps | 240500 |\n", "| train/ | |\n", "| entropy_loss | -0.901 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0103 |\n", "| value_loss | 0.00106 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48200 |\n", "| time_elapsed | 1286 |\n", "| total_timesteps | 241000 |\n", "| train/ | |\n", "| entropy_loss | -0.861 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48300 |\n", "| time_elapsed | 1289 |\n", "| total_timesteps | 241500 |\n", "| train/ | |\n", "| entropy_loss | -0.883 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0123 |\n", "| value_loss | 0.000991 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48400 |\n", "| time_elapsed | 1291 |\n", "| total_timesteps | 242000 |\n", "| train/ | |\n", "| entropy_loss | -0.96 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0238 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48500 |\n", "| time_elapsed | 1294 |\n", "| total_timesteps | 242500 |\n", "| train/ | |\n", "| entropy_loss | -0.966 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.04 |\n", "| value_loss | 0.544 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48600 |\n", "| time_elapsed | 1297 |\n", "| total_timesteps | 243000 |\n", "| train/ | |\n", "| entropy_loss | -0.987 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0117 |\n", "| value_loss | 0.00101 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48700 |\n", "| time_elapsed | 1299 |\n", "| total_timesteps | 243500 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.351 |\n", "| value_loss | 0.727 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48800 |\n", "| time_elapsed | 1302 |\n", "| total_timesteps | 244000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0195 |\n", "| value_loss | 0.000924 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 48900 |\n", "| time_elapsed | 1305 |\n", "| total_timesteps | 244500 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49000 |\n", "| time_elapsed | 1307 |\n", "| total_timesteps | 245000 |\n", "| train/ | |\n", "| entropy_loss | -1.06 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0291 |\n", "| value_loss | 0.000992 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49100 |\n", "| time_elapsed | 1310 |\n", "| total_timesteps | 245500 |\n", "| train/ | |\n", "| entropy_loss | -1.05 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0126 |\n", "| value_loss | 0.000939 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49200 |\n", "| time_elapsed | 1313 |\n", "| total_timesteps | 246000 |\n", "| train/ | |\n", "| entropy_loss | -0.96 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0286 |\n", "| value_loss | 0.00114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49300 |\n", "| time_elapsed | 1315 |\n", "| total_timesteps | 246500 |\n", "| train/ | |\n", "| entropy_loss | -0.948 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0331 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49400 |\n", "| time_elapsed | 1318 |\n", "| total_timesteps | 247000 |\n", "| train/ | |\n", "| entropy_loss | -0.944 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0298 |\n", "| value_loss | 0.00126 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49500 |\n", "| time_elapsed | 1320 |\n", "| total_timesteps | 247500 |\n", "| train/ | |\n", "| entropy_loss | -0.913 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0263 |\n", "| value_loss | 0.00121 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49600 |\n", "| time_elapsed | 1323 |\n", "| total_timesteps | 248000 |\n", "| train/ | |\n", "| entropy_loss | -0.92 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0345 |\n", "| value_loss | 0.0014 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49700 |\n", "| time_elapsed | 1326 |\n", "| total_timesteps | 248500 |\n", "| train/ | |\n", "| entropy_loss | -0.999 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0118 |\n", "| value_loss | 0.000987 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49800 |\n", "| time_elapsed | 1328 |\n", "| total_timesteps | 249000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 505 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 49900 |\n", "| time_elapsed | 1331 |\n", "| total_timesteps | 249500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.2 |\n", "| value_loss | 0.907 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50000 |\n", "| time_elapsed | 1333 |\n", "| total_timesteps | 250000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 1.29 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50100 |\n", "| time_elapsed | 1336 |\n", "| total_timesteps | 250500 |\n", "| train/ | |\n", "| entropy_loss | -1.05 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.00109 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50200 |\n", "| time_elapsed | 1338 |\n", "| total_timesteps | 251000 |\n", "| train/ | |\n", "| entropy_loss | -0.969 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0302 |\n", "| value_loss | 0.0011 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50300 |\n", "| time_elapsed | 1341 |\n", "| total_timesteps | 251500 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0304 |\n", "| value_loss | 0.00115 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50400 |\n", "| time_elapsed | 1344 |\n", "| total_timesteps | 252000 |\n", "| train/ | |\n", "| entropy_loss | -0.91 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0215 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50500 |\n", "| time_elapsed | 1346 |\n", "| total_timesteps | 252500 |\n", "| train/ | |\n", "| entropy_loss | -0.896 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.463 |\n", "| value_loss | 2.03 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50600 |\n", "| time_elapsed | 1349 |\n", "| total_timesteps | 253000 |\n", "| train/ | |\n", "| entropy_loss | -0.951 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.134 |\n", "| value_loss | 0.363 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50700 |\n", "| time_elapsed | 1351 |\n", "| total_timesteps | 253500 |\n", "| train/ | |\n", "| entropy_loss | -0.797 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0296 |\n", "| value_loss | 0.00117 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50800 |\n", "| time_elapsed | 1354 |\n", "| total_timesteps | 254000 |\n", "| train/ | |\n", "| entropy_loss | -0.826 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0202 |\n", "| value_loss | 0.000983 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 50900 |\n", "| time_elapsed | 1357 |\n", "| total_timesteps | 254500 |\n", "| train/ | |\n", "| entropy_loss | -0.901 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0264 |\n", "| value_loss | 0.000828 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51000 |\n", "| time_elapsed | 1359 |\n", "| total_timesteps | 255000 |\n", "| train/ | |\n", "| entropy_loss | -0.87 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0262 |\n", "| value_loss | 0.000784 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 505 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51100 |\n", "| time_elapsed | 1362 |\n", "| total_timesteps | 255500 |\n", "| train/ | |\n", "| entropy_loss | -0.851 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0289 |\n", "| value_loss | 0.000842 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51200 |\n", "| time_elapsed | 1364 |\n", "| total_timesteps | 256000 |\n", "| train/ | |\n", "| entropy_loss | -0.766 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00722 |\n", "| value_loss | 0.000943 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51300 |\n", "| time_elapsed | 1367 |\n", "| total_timesteps | 256500 |\n", "| train/ | |\n", "| entropy_loss | -0.751 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0919 |\n", "| value_loss | 0.359 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 506 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51400 |\n", "| time_elapsed | 1370 |\n", "| total_timesteps | 257000 |\n", "| train/ | |\n", "| entropy_loss | -0.737 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0115 |\n", "| value_loss | 0.00121 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51500 |\n", "| time_elapsed | 1372 |\n", "| total_timesteps | 257500 |\n", "| train/ | |\n", "| entropy_loss | -0.758 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00772 |\n", "| value_loss | 0.00111 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51600 |\n", "| time_elapsed | 1375 |\n", "| total_timesteps | 258000 |\n", "| train/ | |\n", "| entropy_loss | -0.767 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00785 |\n", "| value_loss | 0.00114 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51700 |\n", "| time_elapsed | 1377 |\n", "| total_timesteps | 258500 |\n", "| train/ | |\n", "| entropy_loss | -0.791 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.022 |\n", "| value_loss | 0.00101 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51800 |\n", "| time_elapsed | 1380 |\n", "| total_timesteps | 259000 |\n", "| train/ | |\n", "| entropy_loss | -0.902 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.017 |\n", "| value_loss | 0.000869 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 51900 |\n", "| time_elapsed | 1383 |\n", "| total_timesteps | 259500 |\n", "| train/ | |\n", "| entropy_loss | -0.899 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.000855 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 504 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52000 |\n", "| time_elapsed | 1385 |\n", "| total_timesteps | 260000 |\n", "| train/ | |\n", "| entropy_loss | -0.935 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.000685 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 505 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52100 |\n", "| time_elapsed | 1388 |\n", "| total_timesteps | 260500 |\n", "| train/ | |\n", "| entropy_loss | -0.941 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0381 |\n", "| value_loss | 0.000741 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52200 |\n", "| time_elapsed | 1390 |\n", "| total_timesteps | 261000 |\n", "| train/ | |\n", "| entropy_loss | -0.919 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.336 |\n", "| value_loss | 0.909 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52300 |\n", "| time_elapsed | 1393 |\n", "| total_timesteps | 261500 |\n", "| train/ | |\n", "| entropy_loss | -0.923 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.000797 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52400 |\n", "| time_elapsed | 1396 |\n", "| total_timesteps | 262000 |\n", "| train/ | |\n", "| entropy_loss | -0.883 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0317 |\n", "| value_loss | 0.000824 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52500 |\n", "| time_elapsed | 1398 |\n", "| total_timesteps | 262500 |\n", "| train/ | |\n", "| entropy_loss | -0.861 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0189 |\n", "| value_loss | 0.000811 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52600 |\n", "| time_elapsed | 1401 |\n", "| total_timesteps | 263000 |\n", "| train/ | |\n", "| entropy_loss | -0.895 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0406 |\n", "| value_loss | 0.00078 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52700 |\n", "| time_elapsed | 1403 |\n", "| total_timesteps | 263500 |\n", "| train/ | |\n", "| entropy_loss | -0.853 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0248 |\n", "| value_loss | 0.000849 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52800 |\n", "| time_elapsed | 1406 |\n", "| total_timesteps | 264000 |\n", "| train/ | |\n", "| entropy_loss | -0.953 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0578 |\n", "| value_loss | 0.000767 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 52900 |\n", "| time_elapsed | 1408 |\n", "| total_timesteps | 264500 |\n", "| train/ | |\n", "| entropy_loss | -0.925 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0149 |\n", "| value_loss | 0.000656 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53000 |\n", "| time_elapsed | 1411 |\n", "| total_timesteps | 265000 |\n", "| train/ | |\n", "| entropy_loss | -0.893 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.000682 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53100 |\n", "| time_elapsed | 1414 |\n", "| total_timesteps | 265500 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.027 |\n", "| value_loss | 0.000606 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53200 |\n", "| time_elapsed | 1416 |\n", "| total_timesteps | 266000 |\n", "| train/ | |\n", "| entropy_loss | -0.907 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0256 |\n", "| value_loss | 0.000737 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53300 |\n", "| time_elapsed | 1419 |\n", "| total_timesteps | 266500 |\n", "| train/ | |\n", "| entropy_loss | -0.917 |\n", "| explained_variance | 2.98e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.59 |\n", "| value_loss | 2.05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53400 |\n", "| time_elapsed | 1422 |\n", "| total_timesteps | 267000 |\n", "| train/ | |\n", "| entropy_loss | -0.889 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.547 |\n", "| value_loss | 1.13 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53500 |\n", "| time_elapsed | 1424 |\n", "| total_timesteps | 267500 |\n", "| train/ | |\n", "| entropy_loss | -0.895 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0273 |\n", "| value_loss | 0.000604 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53600 |\n", "| time_elapsed | 1427 |\n", "| total_timesteps | 268000 |\n", "| train/ | |\n", "| entropy_loss | -0.849 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.622 |\n", "| value_loss | 0.184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53700 |\n", "| time_elapsed | 1429 |\n", "| total_timesteps | 268500 |\n", "| train/ | |\n", "| entropy_loss | -0.897 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.194 |\n", "| value_loss | 0.55 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53800 |\n", "| time_elapsed | 1432 |\n", "| total_timesteps | 269000 |\n", "| train/ | |\n", "| entropy_loss | -0.883 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.12 |\n", "| value_loss | 2.05 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 53900 |\n", "| time_elapsed | 1435 |\n", "| total_timesteps | 269500 |\n", "| train/ | |\n", "| entropy_loss | -0.9 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00808 |\n", "| value_loss | 0.000687 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54000 |\n", "| time_elapsed | 1437 |\n", "| total_timesteps | 270000 |\n", "| train/ | |\n", "| entropy_loss | -0.914 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0162 |\n", "| value_loss | 0.000779 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54100 |\n", "| time_elapsed | 1440 |\n", "| total_timesteps | 270500 |\n", "| train/ | |\n", "| entropy_loss | -0.878 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.47 |\n", "| value_loss | 0.548 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54200 |\n", "| time_elapsed | 1442 |\n", "| total_timesteps | 271000 |\n", "| train/ | |\n", "| entropy_loss | -0.854 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00862 |\n", "| value_loss | 0.000882 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54300 |\n", "| time_elapsed | 1445 |\n", "| total_timesteps | 271500 |\n", "| train/ | |\n", "| entropy_loss | -0.926 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0286 |\n", "| value_loss | 0.000861 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54400 |\n", "| time_elapsed | 1448 |\n", "| total_timesteps | 272000 |\n", "| train/ | |\n", "| entropy_loss | -0.964 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0251 |\n", "| value_loss | 0.000786 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54500 |\n", "| time_elapsed | 1450 |\n", "| total_timesteps | 272500 |\n", "| train/ | |\n", "| entropy_loss | -0.995 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0166 |\n", "| value_loss | 0.000776 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54600 |\n", "| time_elapsed | 1453 |\n", "| total_timesteps | 273000 |\n", "| train/ | |\n", "| entropy_loss | -0.93 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0284 |\n", "| value_loss | 0.000645 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54700 |\n", "| time_elapsed | 1456 |\n", "| total_timesteps | 273500 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0166 |\n", "| value_loss | 0.000653 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54800 |\n", "| time_elapsed | 1458 |\n", "| total_timesteps | 274000 |\n", "| train/ | |\n", "| entropy_loss | -0.924 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0261 |\n", "| value_loss | 0.000609 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 54900 |\n", "| time_elapsed | 1461 |\n", "| total_timesteps | 274500 |\n", "| train/ | |\n", "| entropy_loss | -0.897 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.261 |\n", "| value_loss | 0.736 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55000 |\n", "| time_elapsed | 1463 |\n", "| total_timesteps | 275000 |\n", "| train/ | |\n", "| entropy_loss | -0.822 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0192 |\n", "| value_loss | 0.000669 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55100 |\n", "| time_elapsed | 1466 |\n", "| total_timesteps | 275500 |\n", "| train/ | |\n", "| entropy_loss | -0.782 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0201 |\n", "| value_loss | 0.000769 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55200 |\n", "| time_elapsed | 1469 |\n", "| total_timesteps | 276000 |\n", "| train/ | |\n", "| entropy_loss | -0.816 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.000881 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55300 |\n", "| time_elapsed | 1471 |\n", "| total_timesteps | 276500 |\n", "| train/ | |\n", "| entropy_loss | -0.837 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0134 |\n", "| value_loss | 0.00084 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55400 |\n", "| time_elapsed | 1474 |\n", "| total_timesteps | 277000 |\n", "| train/ | |\n", "| entropy_loss | -0.909 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00889 |\n", "| value_loss | 0.000751 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55500 |\n", "| time_elapsed | 1477 |\n", "| total_timesteps | 277500 |\n", "| train/ | |\n", "| entropy_loss | -0.929 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00875 |\n", "| value_loss | 0.000655 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55600 |\n", "| time_elapsed | 1479 |\n", "| total_timesteps | 278000 |\n", "| train/ | |\n", "| entropy_loss | -0.955 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.000775 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55700 |\n", "| time_elapsed | 1482 |\n", "| total_timesteps | 278500 |\n", "| train/ | |\n", "| entropy_loss | -0.915 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00859 |\n", "| value_loss | 0.000679 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55800 |\n", "| time_elapsed | 1484 |\n", "| total_timesteps | 279000 |\n", "| train/ | |\n", "| entropy_loss | -0.945 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00872 |\n", "| value_loss | 0.000607 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 55900 |\n", "| time_elapsed | 1487 |\n", "| total_timesteps | 279500 |\n", "| train/ | |\n", "| entropy_loss | -0.88 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0129 |\n", "| value_loss | 0.000745 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56000 |\n", "| time_elapsed | 1490 |\n", "| total_timesteps | 280000 |\n", "| train/ | |\n", "| entropy_loss | -0.925 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.000666 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56100 |\n", "| time_elapsed | 1492 |\n", "| total_timesteps | 280500 |\n", "| train/ | |\n", "| entropy_loss | -0.874 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00838 |\n", "| value_loss | 0.000701 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56200 |\n", "| time_elapsed | 1495 |\n", "| total_timesteps | 281000 |\n", "| train/ | |\n", "| entropy_loss | -0.843 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0134 |\n", "| value_loss | 0.000613 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56300 |\n", "| time_elapsed | 1497 |\n", "| total_timesteps | 281500 |\n", "| train/ | |\n", "| entropy_loss | -0.841 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00681 |\n", "| value_loss | 0.000536 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56400 |\n", "| time_elapsed | 1500 |\n", "| total_timesteps | 282000 |\n", "| train/ | |\n", "| entropy_loss | -0.812 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.328 |\n", "| value_loss | 0.292 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56500 |\n", "| time_elapsed | 1503 |\n", "| total_timesteps | 282500 |\n", "| train/ | |\n", "| entropy_loss | -0.755 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.556 |\n", "| value_loss | 1.3 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56600 |\n", "| time_elapsed | 1505 |\n", "| total_timesteps | 283000 |\n", "| train/ | |\n", "| entropy_loss | -0.775 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0237 |\n", "| value_loss | 0.000751 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56700 |\n", "| time_elapsed | 1508 |\n", "| total_timesteps | 283500 |\n", "| train/ | |\n", "| entropy_loss | -0.813 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.018 |\n", "| value_loss | 0.000674 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56800 |\n", "| time_elapsed | 1510 |\n", "| total_timesteps | 284000 |\n", "| train/ | |\n", "| entropy_loss | -0.848 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0164 |\n", "| value_loss | 0.000719 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 56900 |\n", "| time_elapsed | 1513 |\n", "| total_timesteps | 284500 |\n", "| train/ | |\n", "| entropy_loss | -0.926 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0311 |\n", "| value_loss | 0.000688 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 57000 |\n", "| time_elapsed | 1516 |\n", "| total_timesteps | 285000 |\n", "| train/ | |\n", "| entropy_loss | -0.918 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0276 |\n", "| value_loss | 0.000671 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 57100 |\n", "| time_elapsed | 1518 |\n", "| total_timesteps | 285500 |\n", "| train/ | |\n", "| entropy_loss | -0.873 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0172 |\n", "| value_loss | 0.000754 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57200 |\n", "| time_elapsed | 1521 |\n", "| total_timesteps | 286000 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0313 |\n", "| value_loss | 0.000674 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57300 |\n", "| time_elapsed | 1523 |\n", "| total_timesteps | 286500 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.035 |\n", "| value_loss | 0.000634 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57400 |\n", "| time_elapsed | 1526 |\n", "| total_timesteps | 287000 |\n", "| train/ | |\n", "| entropy_loss | -0.923 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00838 |\n", "| value_loss | 0.000604 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57500 |\n", "| time_elapsed | 1529 |\n", "| total_timesteps | 287500 |\n", "| train/ | |\n", "| entropy_loss | -0.946 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0329 |\n", "| value_loss | 0.000669 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57600 |\n", "| time_elapsed | 1531 |\n", "| total_timesteps | 288000 |\n", "| train/ | |\n", "| entropy_loss | -0.9 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0201 |\n", "| value_loss | 0.000633 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57700 |\n", "| time_elapsed | 1534 |\n", "| total_timesteps | 288500 |\n", "| train/ | |\n", "| entropy_loss | -0.872 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00961 |\n", "| value_loss | 0.000609 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 188 |\n", "| iterations | 57800 |\n", "| time_elapsed | 1537 |\n", "| total_timesteps | 289000 |\n", "| train/ | |\n", "| entropy_loss | -0.817 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0163 |\n", "| value_loss | 0.000675 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 57900 |\n", "| time_elapsed | 1539 |\n", "| total_timesteps | 289500 |\n", "| train/ | |\n", "| entropy_loss | -0.837 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.54 |\n", "| value_loss | 1.31 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58000 |\n", "| time_elapsed | 1542 |\n", "| total_timesteps | 290000 |\n", "| train/ | |\n", "| entropy_loss | -0.883 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.016 |\n", "| value_loss | 0.000639 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58100 |\n", "| time_elapsed | 1545 |\n", "| total_timesteps | 290500 |\n", "| train/ | |\n", "| entropy_loss | -0.909 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.43 |\n", "| value_loss | 2.06 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58200 |\n", "| time_elapsed | 1548 |\n", "| total_timesteps | 291000 |\n", "| train/ | |\n", "| entropy_loss | -0.92 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00863 |\n", "| value_loss | 0.00062 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58300 |\n", "| time_elapsed | 1551 |\n", "| total_timesteps | 291500 |\n", "| train/ | |\n", "| entropy_loss | -0.886 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00765 |\n", "| value_loss | 0.000564 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58400 |\n", "| time_elapsed | 1553 |\n", "| total_timesteps | 292000 |\n", "| train/ | |\n", "| entropy_loss | -0.932 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00716 |\n", "| value_loss | 0.000415 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58500 |\n", "| time_elapsed | 1556 |\n", "| total_timesteps | 292500 |\n", "| train/ | |\n", "| entropy_loss | -0.947 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0132 |\n", "| value_loss | 0.000419 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58600 |\n", "| time_elapsed | 1559 |\n", "| total_timesteps | 293000 |\n", "| train/ | |\n", "| entropy_loss | -0.929 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.016 |\n", "| value_loss | 0.000604 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58700 |\n", "| time_elapsed | 1562 |\n", "| total_timesteps | 293500 |\n", "| train/ | |\n", "| entropy_loss | -0.916 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.014 |\n", "| value_loss | 0.000593 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58800 |\n", "| time_elapsed | 1564 |\n", "| total_timesteps | 294000 |\n", "| train/ | |\n", "| entropy_loss | -0.94 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.000655 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 58900 |\n", "| time_elapsed | 1567 |\n", "| total_timesteps | 294500 |\n", "| train/ | |\n", "| entropy_loss | -0.962 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0181 |\n", "| value_loss | 0.000607 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59000 |\n", "| time_elapsed | 1570 |\n", "| total_timesteps | 295000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0172 |\n", "| value_loss | 0.00053 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59100 |\n", "| time_elapsed | 1573 |\n", "| total_timesteps | 295500 |\n", "| train/ | |\n", "| entropy_loss | -0.99 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0149 |\n", "| value_loss | 0.000572 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59200 |\n", "| time_elapsed | 1575 |\n", "| total_timesteps | 296000 |\n", "| train/ | |\n", "| entropy_loss | -0.966 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0515 |\n", "| value_loss | 0.000727 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59300 |\n", "| time_elapsed | 1578 |\n", "| total_timesteps | 296500 |\n", "| train/ | |\n", "| entropy_loss | -0.895 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0441 |\n", "| value_loss | 0.000723 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59400 |\n", "| time_elapsed | 1581 |\n", "| total_timesteps | 297000 |\n", "| train/ | |\n", "| entropy_loss | -0.843 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.022 |\n", "| value_loss | 0.000696 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59500 |\n", "| time_elapsed | 1583 |\n", "| total_timesteps | 297500 |\n", "| train/ | |\n", "| entropy_loss | -0.886 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00822 |\n", "| value_loss | 0.000694 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59600 |\n", "| time_elapsed | 1586 |\n", "| total_timesteps | 298000 |\n", "| train/ | |\n", "| entropy_loss | -0.898 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.000744 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59700 |\n", "| time_elapsed | 1589 |\n", "| total_timesteps | 298500 |\n", "| train/ | |\n", "| entropy_loss | -0.935 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00889 |\n", "| value_loss | 0.000683 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59800 |\n", "| time_elapsed | 1592 |\n", "| total_timesteps | 299000 |\n", "| train/ | |\n", "| entropy_loss | -0.967 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0156 |\n", "| value_loss | 0.000691 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 59900 |\n", "| time_elapsed | 1594 |\n", "| total_timesteps | 299500 |\n", "| train/ | |\n", "| entropy_loss | -0.941 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.36 |\n", "| value_loss | 2.61 |\n", "------------------------------------\n", "Eval num_timesteps=300000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 300000 |\n", "| train/ | |\n", "| entropy_loss | -0.932 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.872 |\n", "| value_loss | 1.3 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60000 |\n", "| time_elapsed | 1608 |\n", "| total_timesteps | 300000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60100 |\n", "| time_elapsed | 1611 |\n", "| total_timesteps | 300500 |\n", "| train/ | |\n", "| entropy_loss | -0.934 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0221 |\n", "| value_loss | 0.0009 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60200 |\n", "| time_elapsed | 1613 |\n", "| total_timesteps | 301000 |\n", "| train/ | |\n", "| entropy_loss | -0.927 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.000899 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60300 |\n", "| time_elapsed | 1616 |\n", "| total_timesteps | 301500 |\n", "| train/ | |\n", "| entropy_loss | -0.918 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.471 |\n", "| value_loss | 0.545 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60400 |\n", "| time_elapsed | 1619 |\n", "| total_timesteps | 302000 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0111 |\n", "| value_loss | 0.000848 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60500 |\n", "| time_elapsed | 1622 |\n", "| total_timesteps | 302500 |\n", "| train/ | |\n", "| entropy_loss | -0.952 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.019 |\n", "| value_loss | 0.000829 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60600 |\n", "| time_elapsed | 1624 |\n", "| total_timesteps | 303000 |\n", "| train/ | |\n", "| entropy_loss | -0.952 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.29 |\n", "| value_loss | 0.908 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60700 |\n", "| time_elapsed | 1627 |\n", "| total_timesteps | 303500 |\n", "| train/ | |\n", "| entropy_loss | -0.906 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.000949 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60800 |\n", "| time_elapsed | 1629 |\n", "| total_timesteps | 304000 |\n", "| train/ | |\n", "| entropy_loss | -0.835 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 60900 |\n", "| time_elapsed | 1632 |\n", "| total_timesteps | 304500 |\n", "| train/ | |\n", "| entropy_loss | -0.924 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.016 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 12.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61000 |\n", "| time_elapsed | 1635 |\n", "| total_timesteps | 305000 |\n", "| train/ | |\n", "| entropy_loss | -0.927 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0106 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61100 |\n", "| time_elapsed | 1637 |\n", "| total_timesteps | 305500 |\n", "| train/ | |\n", "| entropy_loss | -0.898 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61200 |\n", "| time_elapsed | 1640 |\n", "| total_timesteps | 306000 |\n", "| train/ | |\n", "| entropy_loss | -0.832 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0217 |\n", "| value_loss | 0.00106 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61300 |\n", "| time_elapsed | 1643 |\n", "| total_timesteps | 306500 |\n", "| train/ | |\n", "| entropy_loss | -0.78 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0191 |\n", "| value_loss | 0.00116 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61400 |\n", "| time_elapsed | 1645 |\n", "| total_timesteps | 307000 |\n", "| train/ | |\n", "| entropy_loss | -0.796 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0201 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61500 |\n", "| time_elapsed | 1648 |\n", "| total_timesteps | 307500 |\n", "| train/ | |\n", "| entropy_loss | -0.811 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00843 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61600 |\n", "| time_elapsed | 1651 |\n", "| total_timesteps | 308000 |\n", "| train/ | |\n", "| entropy_loss | -0.801 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.023 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61700 |\n", "| time_elapsed | 1653 |\n", "| total_timesteps | 308500 |\n", "| train/ | |\n", "| entropy_loss | -0.819 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0214 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61800 |\n", "| time_elapsed | 1656 |\n", "| total_timesteps | 309000 |\n", "| train/ | |\n", "| entropy_loss | -0.876 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.000981 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 61900 |\n", "| time_elapsed | 1658 |\n", "| total_timesteps | 309500 |\n", "| train/ | |\n", "| entropy_loss | -0.845 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0126 |\n", "| value_loss | 0.00112 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62000 |\n", "| time_elapsed | 1661 |\n", "| total_timesteps | 310000 |\n", "| train/ | |\n", "| entropy_loss | -0.885 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0375 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62100 |\n", "| time_elapsed | 1664 |\n", "| total_timesteps | 310500 |\n", "| train/ | |\n", "| entropy_loss | -0.864 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0253 |\n", "| value_loss | 0.000988 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62200 |\n", "| time_elapsed | 1666 |\n", "| total_timesteps | 311000 |\n", "| train/ | |\n", "| entropy_loss | -0.854 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62300 |\n", "| time_elapsed | 1669 |\n", "| total_timesteps | 311500 |\n", "| train/ | |\n", "| entropy_loss | -0.882 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0172 |\n", "| value_loss | 0.000904 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62400 |\n", "| time_elapsed | 1672 |\n", "| total_timesteps | 312000 |\n", "| train/ | |\n", "| entropy_loss | -0.782 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00805 |\n", "| value_loss | 0.00107 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62500 |\n", "| time_elapsed | 1674 |\n", "| total_timesteps | 312500 |\n", "| train/ | |\n", "| entropy_loss | -0.796 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00857 |\n", "| value_loss | 0.00113 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62600 |\n", "| time_elapsed | 1677 |\n", "| total_timesteps | 313000 |\n", "| train/ | |\n", "| entropy_loss | -0.762 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00758 |\n", "| value_loss | 0.00102 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62700 |\n", "| time_elapsed | 1680 |\n", "| total_timesteps | 313500 |\n", "| train/ | |\n", "| entropy_loss | -0.741 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.191 |\n", "| value_loss | 0.724 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62800 |\n", "| time_elapsed | 1682 |\n", "| total_timesteps | 314000 |\n", "| train/ | |\n", "| entropy_loss | -0.807 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0285 |\n", "| value_loss | 0.000928 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 62900 |\n", "| time_elapsed | 1685 |\n", "| total_timesteps | 314500 |\n", "| train/ | |\n", "| entropy_loss | -0.845 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.000893 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63000 |\n", "| time_elapsed | 1688 |\n", "| total_timesteps | 315000 |\n", "| train/ | |\n", "| entropy_loss | -0.862 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.000768 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63100 |\n", "| time_elapsed | 1690 |\n", "| total_timesteps | 315500 |\n", "| train/ | |\n", "| entropy_loss | -0.917 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.000853 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 490 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63200 |\n", "| time_elapsed | 1693 |\n", "| total_timesteps | 316000 |\n", "| train/ | |\n", "| entropy_loss | -0.94 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0184 |\n", "| value_loss | 0.000767 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63300 |\n", "| time_elapsed | 1695 |\n", "| total_timesteps | 316500 |\n", "| train/ | |\n", "| entropy_loss | -0.927 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0337 |\n", "| value_loss | 0.000757 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63400 |\n", "| time_elapsed | 1698 |\n", "| total_timesteps | 317000 |\n", "| train/ | |\n", "| entropy_loss | -0.959 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00972 |\n", "| value_loss | 0.00074 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63500 |\n", "| time_elapsed | 1701 |\n", "| total_timesteps | 317500 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0307 |\n", "| value_loss | 0.000718 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63600 |\n", "| time_elapsed | 1703 |\n", "| total_timesteps | 318000 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0197 |\n", "| value_loss | 0.000714 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63700 |\n", "| time_elapsed | 1706 |\n", "| total_timesteps | 318500 |\n", "| train/ | |\n", "| entropy_loss | -0.959 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0232 |\n", "| value_loss | 0.000691 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63800 |\n", "| time_elapsed | 1708 |\n", "| total_timesteps | 319000 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.000638 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 63900 |\n", "| time_elapsed | 1711 |\n", "| total_timesteps | 319500 |\n", "| train/ | |\n", "| entropy_loss | -0.964 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.00897 |\n", "| value_loss | 0.000617 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64000 |\n", "| time_elapsed | 1714 |\n", "| total_timesteps | 320000 |\n", "| train/ | |\n", "| entropy_loss | -0.969 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0261 |\n", "| value_loss | 0.000614 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64100 |\n", "| time_elapsed | 1716 |\n", "| total_timesteps | 320500 |\n", "| train/ | |\n", "| entropy_loss | -0.975 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.26 |\n", "| value_loss | 0.917 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64200 |\n", "| time_elapsed | 1719 |\n", "| total_timesteps | 321000 |\n", "| train/ | |\n", "| entropy_loss | -0.975 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0103 |\n", "| value_loss | 0.000773 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64300 |\n", "| time_elapsed | 1721 |\n", "| total_timesteps | 321500 |\n", "| train/ | |\n", "| entropy_loss | -0.987 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0255 |\n", "| value_loss | 0.000711 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64400 |\n", "| time_elapsed | 1724 |\n", "| total_timesteps | 322000 |\n", "| train/ | |\n", "| entropy_loss | -0.954 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0137 |\n", "| value_loss | 0.000802 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64500 |\n", "| time_elapsed | 1727 |\n", "| total_timesteps | 322500 |\n", "| train/ | |\n", "| entropy_loss | -0.953 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0184 |\n", "| value_loss | 0.000775 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64600 |\n", "| time_elapsed | 1729 |\n", "| total_timesteps | 323000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0294 |\n", "| value_loss | 0.000751 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64700 |\n", "| time_elapsed | 1732 |\n", "| total_timesteps | 323500 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0126 |\n", "| value_loss | 0.000694 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64800 |\n", "| time_elapsed | 1734 |\n", "| total_timesteps | 324000 |\n", "| train/ | |\n", "| entropy_loss | -1.02 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.000743 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 64900 |\n", "| time_elapsed | 1737 |\n", "| total_timesteps | 324500 |\n", "| train/ | |\n", "| entropy_loss | -1.01 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0302 |\n", "| value_loss | 0.000672 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65000 |\n", "| time_elapsed | 1740 |\n", "| total_timesteps | 325000 |\n", "| train/ | |\n", "| entropy_loss | -0.954 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.01 |\n", "| value_loss | 0.000832 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65100 |\n", "| time_elapsed | 1742 |\n", "| total_timesteps | 325500 |\n", "| train/ | |\n", "| entropy_loss | -0.883 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0122 |\n", "| value_loss | 0.00095 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65200 |\n", "| time_elapsed | 1745 |\n", "| total_timesteps | 326000 |\n", "| train/ | |\n", "| entropy_loss | -0.902 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0248 |\n", "| value_loss | 0.00106 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65300 |\n", "| time_elapsed | 1747 |\n", "| total_timesteps | 326500 |\n", "| train/ | |\n", "| entropy_loss | -0.93 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0103 |\n", "| value_loss | 0.000961 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 485 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65400 |\n", "| time_elapsed | 1750 |\n", "| total_timesteps | 327000 |\n", "| train/ | |\n", "| entropy_loss | -0.936 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0341 |\n", "| value_loss | 0.000951 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65500 |\n", "| time_elapsed | 1752 |\n", "| total_timesteps | 327500 |\n", "| train/ | |\n", "| entropy_loss | -0.927 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65600 |\n", "| time_elapsed | 1755 |\n", "| total_timesteps | 328000 |\n", "| train/ | |\n", "| entropy_loss | -0.936 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0105 |\n", "| value_loss | 0.00094 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65700 |\n", "| time_elapsed | 1758 |\n", "| total_timesteps | 328500 |\n", "| train/ | |\n", "| entropy_loss | -0.947 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.000961 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65800 |\n", "| time_elapsed | 1760 |\n", "| total_timesteps | 329000 |\n", "| train/ | |\n", "| entropy_loss | -0.982 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0168 |\n", "| value_loss | 0.00101 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 65900 |\n", "| time_elapsed | 1763 |\n", "| total_timesteps | 329500 |\n", "| train/ | |\n", "| entropy_loss | -0.943 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0406 |\n", "| value_loss | 0.00108 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66000 |\n", "| time_elapsed | 1765 |\n", "| total_timesteps | 330000 |\n", "| train/ | |\n", "| entropy_loss | -0.98 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66100 |\n", "| time_elapsed | 1768 |\n", "| total_timesteps | 330500 |\n", "| train/ | |\n", "| entropy_loss | -1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0198 |\n", "| value_loss | 0.00105 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66200 |\n", "| time_elapsed | 1771 |\n", "| total_timesteps | 331000 |\n", "| train/ | |\n", "| entropy_loss | -1.03 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66300 |\n", "| time_elapsed | 1773 |\n", "| total_timesteps | 331500 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0335 |\n", "| value_loss | 0.000904 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 488 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66400 |\n", "| time_elapsed | 1776 |\n", "| total_timesteps | 332000 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0231 |\n", "| value_loss | 0.000974 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66500 |\n", "| time_elapsed | 1778 |\n", "| total_timesteps | 332500 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0146 |\n", "| value_loss | 0.00102 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66600 |\n", "| time_elapsed | 1781 |\n", "| total_timesteps | 333000 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0645 |\n", "| value_loss | 0.000976 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66700 |\n", "| time_elapsed | 1783 |\n", "| total_timesteps | 333500 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0259 |\n", "| value_loss | 0.000935 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66800 |\n", "| time_elapsed | 1786 |\n", "| total_timesteps | 334000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.02 |\n", "| value_loss | 1.3 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 483 |\n", "| ep_rew_mean | 11.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 66900 |\n", "| time_elapsed | 1789 |\n", "| total_timesteps | 334500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0374 |\n", "| value_loss | 0.000939 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67000 |\n", "| time_elapsed | 1791 |\n", "| total_timesteps | 335000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0277 |\n", "| value_loss | 0.000911 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 484 |\n", "| ep_rew_mean | 11.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67100 |\n", "| time_elapsed | 1794 |\n", "| total_timesteps | 335500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0328 |\n", "| value_loss | 0.000954 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67200 |\n", "| time_elapsed | 1796 |\n", "| total_timesteps | 336000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0336 |\n", "| value_loss | 0.00106 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67300 |\n", "| time_elapsed | 1799 |\n", "| total_timesteps | 336500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.015 |\n", "| value_loss | 0.000974 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67400 |\n", "| time_elapsed | 1802 |\n", "| total_timesteps | 337000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0281 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 487 |\n", "| ep_rew_mean | 11.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 67500 |\n", "| time_elapsed | 1804 |\n", "| total_timesteps | 337500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0341 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 486 |\n", "| ep_rew_mean | 11.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 67600 |\n", "| time_elapsed | 1807 |\n", "| total_timesteps | 338000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 37.1 |\n", "| value_loss | 383 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 489 |\n", "| ep_rew_mean | 12.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 67700 |\n", "| time_elapsed | 1809 |\n", "| total_timesteps | 338500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0412 |\n", "| value_loss | 0.00115 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 67800 |\n", "| time_elapsed | 1812 |\n", "| total_timesteps | 339000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 67900 |\n", "| time_elapsed | 1815 |\n", "| total_timesteps | 339500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0467 |\n", "| value_loss | 0.00133 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68000 |\n", "| time_elapsed | 1817 |\n", "| total_timesteps | 340000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0376 |\n", "| value_loss | 0.00123 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68100 |\n", "| time_elapsed | 1820 |\n", "| total_timesteps | 340500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00127 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 12.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68200 |\n", "| time_elapsed | 1822 |\n", "| total_timesteps | 341000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0218 |\n", "| value_loss | 0.00126 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68300 |\n", "| time_elapsed | 1825 |\n", "| total_timesteps | 341500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.022 |\n", "| value_loss | 0.00123 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68400 |\n", "| time_elapsed | 1828 |\n", "| total_timesteps | 342000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.1 |\n", "| value_loss | 0.903 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68500 |\n", "| time_elapsed | 1830 |\n", "| total_timesteps | 342500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68600 |\n", "| time_elapsed | 1833 |\n", "| total_timesteps | 343000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0453 |\n", "| value_loss | 0.00134 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68700 |\n", "| time_elapsed | 1835 |\n", "| total_timesteps | 343500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.00133 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68800 |\n", "| time_elapsed | 1838 |\n", "| total_timesteps | 344000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0325 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 68900 |\n", "| time_elapsed | 1840 |\n", "| total_timesteps | 344500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.994 |\n", "| value_loss | 0.901 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69000 |\n", "| time_elapsed | 1843 |\n", "| total_timesteps | 345000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0304 |\n", "| value_loss | 0.00121 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 491 |\n", "| ep_rew_mean | 12.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69100 |\n", "| time_elapsed | 1846 |\n", "| total_timesteps | 345500 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.32 |\n", "| value_loss | 2.03 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 12.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69200 |\n", "| time_elapsed | 1848 |\n", "| total_timesteps | 346000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.00123 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69300 |\n", "| time_elapsed | 1851 |\n", "| total_timesteps | 346500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0241 |\n", "| value_loss | 0.00126 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69400 |\n", "| time_elapsed | 1853 |\n", "| total_timesteps | 347000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00144 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 492 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69500 |\n", "| time_elapsed | 1856 |\n", "| total_timesteps | 347500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0369 |\n", "| value_loss | 0.00136 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69600 |\n", "| time_elapsed | 1858 |\n", "| total_timesteps | 348000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00134 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69700 |\n", "| time_elapsed | 1861 |\n", "| total_timesteps | 348500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00137 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69800 |\n", "| time_elapsed | 1864 |\n", "| total_timesteps | 349000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0325 |\n", "| value_loss | 0.00123 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 69900 |\n", "| time_elapsed | 1866 |\n", "| total_timesteps | 349500 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70000 |\n", "| time_elapsed | 1869 |\n", "| total_timesteps | 350000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70100 |\n", "| time_elapsed | 1871 |\n", "| total_timesteps | 350500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.0013 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70200 |\n", "| time_elapsed | 1874 |\n", "| total_timesteps | 351000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0322 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70300 |\n", "| time_elapsed | 1876 |\n", "| total_timesteps | 351500 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0247 |\n", "| value_loss | 0.00117 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 494 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70400 |\n", "| time_elapsed | 1879 |\n", "| total_timesteps | 352000 |\n", "| train/ | |\n", "| entropy_loss | -1.32 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0343 |\n", "| value_loss | 0.00125 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 493 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70500 |\n", "| time_elapsed | 1881 |\n", "| total_timesteps | 352500 |\n", "| train/ | |\n", "| entropy_loss | -1.32 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.572 |\n", "| value_loss | 0.537 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 495 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70600 |\n", "| time_elapsed | 1884 |\n", "| total_timesteps | 353000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00143 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70700 |\n", "| time_elapsed | 1886 |\n", "| total_timesteps | 353500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0281 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70800 |\n", "| time_elapsed | 1889 |\n", "| total_timesteps | 354000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.00129 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 70900 |\n", "| time_elapsed | 1892 |\n", "| total_timesteps | 354500 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00137 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71000 |\n", "| time_elapsed | 1894 |\n", "| total_timesteps | 355000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00139 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 496 |\n", "| ep_rew_mean | 13.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71100 |\n", "| time_elapsed | 1897 |\n", "| total_timesteps | 355500 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71200 |\n", "| time_elapsed | 1899 |\n", "| total_timesteps | 356000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0464 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 497 |\n", "| ep_rew_mean | 13.3 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71300 |\n", "| time_elapsed | 1902 |\n", "| total_timesteps | 356500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00162 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 498 |\n", "| ep_rew_mean | 13.4 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71400 |\n", "| time_elapsed | 1904 |\n", "| total_timesteps | 357000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.48 |\n", "| value_loss | 2.4 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71500 |\n", "| time_elapsed | 1907 |\n", "| total_timesteps | 357500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71600 |\n", "| time_elapsed | 1909 |\n", "| total_timesteps | 358000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71700 |\n", "| time_elapsed | 1912 |\n", "| total_timesteps | 358500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.059 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71800 |\n", "| time_elapsed | 1915 |\n", "| total_timesteps | 359000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0394 |\n", "| value_loss | 0.00163 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 71900 |\n", "| time_elapsed | 1917 |\n", "| total_timesteps | 359500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72000 |\n", "| time_elapsed | 1920 |\n", "| total_timesteps | 360000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0229 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72100 |\n", "| time_elapsed | 1923 |\n", "| total_timesteps | 360500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72200 |\n", "| time_elapsed | 1925 |\n", "| total_timesteps | 361000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72300 |\n", "| time_elapsed | 1928 |\n", "| total_timesteps | 361500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72400 |\n", "| time_elapsed | 1930 |\n", "| total_timesteps | 362000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72500 |\n", "| time_elapsed | 1933 |\n", "| total_timesteps | 362500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72600 |\n", "| time_elapsed | 1936 |\n", "| total_timesteps | 363000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00164 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72700 |\n", "| time_elapsed | 1938 |\n", "| total_timesteps | 363500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0335 |\n", "| value_loss | 0.00164 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72800 |\n", "| time_elapsed | 1941 |\n", "| total_timesteps | 364000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.1 |\n", "| value_loss | 0.00156 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 72900 |\n", "| time_elapsed | 1943 |\n", "| total_timesteps | 364500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73000 |\n", "| time_elapsed | 1946 |\n", "| total_timesteps | 365000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.028 |\n", "| value_loss | 0.00148 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73100 |\n", "| time_elapsed | 1949 |\n", "| total_timesteps | 365500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00138 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73200 |\n", "| time_elapsed | 1951 |\n", "| total_timesteps | 366000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.00139 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 499 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73300 |\n", "| time_elapsed | 1954 |\n", "| total_timesteps | 366500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00129 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 500 |\n", "| ep_rew_mean | 13.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73400 |\n", "| time_elapsed | 1956 |\n", "| total_timesteps | 367000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.0012 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 14 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73500 |\n", "| time_elapsed | 1959 |\n", "| total_timesteps | 367500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 14 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73600 |\n", "| time_elapsed | 1962 |\n", "| total_timesteps | 368000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0302 |\n", "| value_loss | 0.00127 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 14 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73700 |\n", "| time_elapsed | 1964 |\n", "| total_timesteps | 368500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0376 |\n", "| value_loss | 0.00128 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 501 |\n", "| ep_rew_mean | 14.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73800 |\n", "| time_elapsed | 1967 |\n", "| total_timesteps | 369000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00142 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 502 |\n", "| ep_rew_mean | 14.2 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 73900 |\n", "| time_elapsed | 1969 |\n", "| total_timesteps | 369500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00143 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 505 |\n", "| ep_rew_mean | 14.6 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74000 |\n", "| time_elapsed | 1972 |\n", "| total_timesteps | 370000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00131 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74100 |\n", "| time_elapsed | 1975 |\n", "| total_timesteps | 370500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0589 |\n", "| value_loss | 0.00124 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74200 |\n", "| time_elapsed | 1977 |\n", "| total_timesteps | 371000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.00122 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 503 |\n", "| ep_rew_mean | 14.5 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74300 |\n", "| time_elapsed | 1980 |\n", "| total_timesteps | 371500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 505 |\n", "| ep_rew_mean | 14.7 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74400 |\n", "| time_elapsed | 1983 |\n", "| total_timesteps | 372000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0508 |\n", "| value_loss | 0.00154 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 506 |\n", "| ep_rew_mean | 14.8 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74500 |\n", "| time_elapsed | 1985 |\n", "| total_timesteps | 372500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.806 |\n", "| value_loss | 0.891 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 14.9 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74600 |\n", "| time_elapsed | 1988 |\n", "| total_timesteps | 373000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00153 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74700 |\n", "| time_elapsed | 1991 |\n", "| total_timesteps | 373500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 15 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74800 |\n", "| time_elapsed | 1993 |\n", "| total_timesteps | 374000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 187 |\n", "| iterations | 74900 |\n", "| time_elapsed | 1996 |\n", "| total_timesteps | 374500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "Eval num_timesteps=375000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 375000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00161 |\n", "------------------------------------\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/opt/conda/lib/python3.10/site-packages/gymnasium/utils/passive_env_checker.py:335: UserWarning: \u001b[33mWARN: No render fps was declared in the environment (env.metadata['render_fps'] is None or not defined), rendering may occur at inconsistent fps.\u001b[0m\n", " logger.warn(\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75000 |\n", "| time_elapsed | 2010 |\n", "| total_timesteps | 375000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75100 |\n", "| time_elapsed | 2016 |\n", "| total_timesteps | 375500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00163 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75200 |\n", "| time_elapsed | 2019 |\n", "| total_timesteps | 376000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0521 |\n", "| value_loss | 0.00145 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75300 |\n", "| time_elapsed | 2021 |\n", "| total_timesteps | 376500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.234 |\n", "| value_loss | 0.355 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75400 |\n", "| time_elapsed | 2024 |\n", "| total_timesteps | 377000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00146 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75500 |\n", "| time_elapsed | 2027 |\n", "| total_timesteps | 377500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0439 |\n", "| value_loss | 0.0015 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75600 |\n", "| time_elapsed | 2029 |\n", "| total_timesteps | 378000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.268 |\n", "| value_loss | 0.179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75700 |\n", "| time_elapsed | 2032 |\n", "| total_timesteps | 378500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00149 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75800 |\n", "| time_elapsed | 2035 |\n", "| total_timesteps | 379000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00159 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 75900 |\n", "| time_elapsed | 2037 |\n", "| total_timesteps | 379500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00163 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76000 |\n", "| time_elapsed | 2040 |\n", "| total_timesteps | 380000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00149 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76100 |\n", "| time_elapsed | 2043 |\n", "| total_timesteps | 380500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0369 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76200 |\n", "| time_elapsed | 2046 |\n", "| total_timesteps | 381000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0341 |\n", "| value_loss | 0.00145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76300 |\n", "| time_elapsed | 2048 |\n", "| total_timesteps | 381500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00146 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76400 |\n", "| time_elapsed | 2051 |\n", "| total_timesteps | 382000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00143 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76500 |\n", "| time_elapsed | 2053 |\n", "| total_timesteps | 382500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00144 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76600 |\n", "| time_elapsed | 2056 |\n", "| total_timesteps | 383000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.034 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76700 |\n", "| time_elapsed | 2059 |\n", "| total_timesteps | 383500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0377 |\n", "| value_loss | 0.00146 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76800 |\n", "| time_elapsed | 2061 |\n", "| total_timesteps | 384000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00138 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 76900 |\n", "| time_elapsed | 2064 |\n", "| total_timesteps | 384500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0315 |\n", "| value_loss | 0.00159 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77000 |\n", "| time_elapsed | 2067 |\n", "| total_timesteps | 385000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00158 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77100 |\n", "| time_elapsed | 2070 |\n", "| total_timesteps | 385500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00153 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77200 |\n", "| time_elapsed | 2072 |\n", "| total_timesteps | 386000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.00149 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77300 |\n", "| time_elapsed | 2075 |\n", "| total_timesteps | 386500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00164 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77400 |\n", "| time_elapsed | 2078 |\n", "| total_timesteps | 387000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77500 |\n", "| time_elapsed | 2081 |\n", "| total_timesteps | 387500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77600 |\n", "| time_elapsed | 2083 |\n", "| total_timesteps | 388000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0568 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77700 |\n", "| time_elapsed | 2086 |\n", "| total_timesteps | 388500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77800 |\n", "| time_elapsed | 2089 |\n", "| total_timesteps | 389000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.101 |\n", "| value_loss | 0.175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 77900 |\n", "| time_elapsed | 2091 |\n", "| total_timesteps | 389500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0581 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78000 |\n", "| time_elapsed | 2094 |\n", "| total_timesteps | 390000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78100 |\n", "| time_elapsed | 2097 |\n", "| total_timesteps | 390500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.531 |\n", "| value_loss | 0.53 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78200 |\n", "| time_elapsed | 2099 |\n", "| total_timesteps | 391000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.24 |\n", "| value_loss | 0.177 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78300 |\n", "| time_elapsed | 2102 |\n", "| total_timesteps | 391500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.11 |\n", "| value_loss | 1.27 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 15.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78400 |\n", "| time_elapsed | 2105 |\n", "| total_timesteps | 392000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78500 |\n", "| time_elapsed | 2107 |\n", "| total_timesteps | 392500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0773 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 507 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78600 |\n", "| time_elapsed | 2110 |\n", "| total_timesteps | 393000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00186 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78700 |\n", "| time_elapsed | 2113 |\n", "| total_timesteps | 393500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.01 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78800 |\n", "| time_elapsed | 2115 |\n", "| total_timesteps | 394000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0417 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 508 |\n", "| ep_rew_mean | 15.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 78900 |\n", "| time_elapsed | 2118 |\n", "| total_timesteps | 394500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79000 |\n", "| time_elapsed | 2121 |\n", "| total_timesteps | 395000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0654 |\n", "| value_loss | 0.00166 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79100 |\n", "| time_elapsed | 2123 |\n", "| total_timesteps | 395500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.385 |\n", "| value_loss | 0.354 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 509 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79200 |\n", "| time_elapsed | 2126 |\n", "| total_timesteps | 396000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00166 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79300 |\n", "| time_elapsed | 2128 |\n", "| total_timesteps | 396500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0547 |\n", "| value_loss | 0.00153 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79400 |\n", "| time_elapsed | 2131 |\n", "| total_timesteps | 397000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.758 |\n", "| value_loss | 0.535 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 510 |\n", "| ep_rew_mean | 15.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79500 |\n", "| time_elapsed | 2134 |\n", "| total_timesteps | 397500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.00161 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79600 |\n", "| time_elapsed | 2136 |\n", "| total_timesteps | 398000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.912 |\n", "| value_loss | 1.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 511 |\n", "| ep_rew_mean | 15.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79700 |\n", "| time_elapsed | 2139 |\n", "| total_timesteps | 398500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79800 |\n", "| time_elapsed | 2142 |\n", "| total_timesteps | 399000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 512 |\n", "| ep_rew_mean | 15.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 79900 |\n", "| time_elapsed | 2144 |\n", "| total_timesteps | 399500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80000 |\n", "| time_elapsed | 2147 |\n", "| total_timesteps | 400000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00204 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80100 |\n", "| time_elapsed | 2150 |\n", "| total_timesteps | 400500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 16 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80200 |\n", "| time_elapsed | 2152 |\n", "| total_timesteps | 401000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80300 |\n", "| time_elapsed | 2155 |\n", "| total_timesteps | 401500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0488 |\n", "| value_loss | 0.00188 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80400 |\n", "| time_elapsed | 2158 |\n", "| total_timesteps | 402000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80500 |\n", "| time_elapsed | 2160 |\n", "| total_timesteps | 402500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0769 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80600 |\n", "| time_elapsed | 2163 |\n", "| total_timesteps | 403000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80700 |\n", "| time_elapsed | 2166 |\n", "| total_timesteps | 403500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80800 |\n", "| time_elapsed | 2169 |\n", "| total_timesteps | 404000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.367 |\n", "| value_loss | 0.352 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 80900 |\n", "| time_elapsed | 2171 |\n", "| total_timesteps | 404500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0599 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81000 |\n", "| time_elapsed | 2174 |\n", "| total_timesteps | 405000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81100 |\n", "| time_elapsed | 2177 |\n", "| total_timesteps | 405500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0396 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81200 |\n", "| time_elapsed | 2179 |\n", "| total_timesteps | 406000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0486 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81300 |\n", "| time_elapsed | 2182 |\n", "| total_timesteps | 406500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0372 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81400 |\n", "| time_elapsed | 2185 |\n", "| total_timesteps | 407000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0366 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81500 |\n", "| time_elapsed | 2187 |\n", "| total_timesteps | 407500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0372 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81600 |\n", "| time_elapsed | 2190 |\n", "| total_timesteps | 408000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81700 |\n", "| time_elapsed | 2193 |\n", "| total_timesteps | 408500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.07 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81800 |\n", "| time_elapsed | 2195 |\n", "| total_timesteps | 409000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.047 |\n", "| value_loss | 0.00165 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 81900 |\n", "| time_elapsed | 2198 |\n", "| total_timesteps | 409500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0487 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82000 |\n", "| time_elapsed | 2201 |\n", "| total_timesteps | 410000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.056 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82100 |\n", "| time_elapsed | 2203 |\n", "| total_timesteps | 410500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0345 |\n", "| value_loss | 0.00181 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82200 |\n", "| time_elapsed | 2206 |\n", "| total_timesteps | 411000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82300 |\n", "| time_elapsed | 2209 |\n", "| total_timesteps | 411500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0549 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82400 |\n", "| time_elapsed | 2211 |\n", "| total_timesteps | 412000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82500 |\n", "| time_elapsed | 2214 |\n", "| total_timesteps | 412500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82600 |\n", "| time_elapsed | 2217 |\n", "| total_timesteps | 413000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0396 |\n", "| value_loss | 0.00138 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82700 |\n", "| time_elapsed | 2219 |\n", "| total_timesteps | 413500 |\n", "| train/ | |\n", "| entropy_loss | -1.34 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00107 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82800 |\n", "| time_elapsed | 2222 |\n", "| total_timesteps | 414000 |\n", "| train/ | |\n", "| entropy_loss | -1.37 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.000806 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 82900 |\n", "| time_elapsed | 2224 |\n", "| total_timesteps | 414500 |\n", "| train/ | |\n", "| entropy_loss | -1.35 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.000909 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83000 |\n", "| time_elapsed | 2227 |\n", "| total_timesteps | 415000 |\n", "| train/ | |\n", "| entropy_loss | -1.35 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0343 |\n", "| value_loss | 0.000956 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83100 |\n", "| time_elapsed | 2230 |\n", "| total_timesteps | 415500 |\n", "| train/ | |\n", "| entropy_loss | -1.35 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0408 |\n", "| value_loss | 0.000961 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83200 |\n", "| time_elapsed | 2233 |\n", "| total_timesteps | 416000 |\n", "| train/ | |\n", "| entropy_loss | -1.33 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00104 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83300 |\n", "| time_elapsed | 2235 |\n", "| total_timesteps | 416500 |\n", "| train/ | |\n", "| entropy_loss | -1.34 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00103 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83400 |\n", "| time_elapsed | 2238 |\n", "| total_timesteps | 417000 |\n", "| train/ | |\n", "| entropy_loss | -1.32 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0338 |\n", "| value_loss | 0.00105 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83500 |\n", "| time_elapsed | 2241 |\n", "| total_timesteps | 417500 |\n", "| train/ | |\n", "| entropy_loss | -1.32 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0324 |\n", "| value_loss | 0.00107 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 16.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83600 |\n", "| time_elapsed | 2243 |\n", "| total_timesteps | 418000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0281 |\n", "| value_loss | 0.00123 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83700 |\n", "| time_elapsed | 2246 |\n", "| total_timesteps | 418500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00132 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83800 |\n", "| time_elapsed | 2249 |\n", "| total_timesteps | 419000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00133 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 83900 |\n", "| time_elapsed | 2251 |\n", "| total_timesteps | 419500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00135 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84000 |\n", "| time_elapsed | 2254 |\n", "| total_timesteps | 420000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0357 |\n", "| value_loss | 0.00141 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84100 |\n", "| time_elapsed | 2257 |\n", "| total_timesteps | 420500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0513 |\n", "| value_loss | 0.00144 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84200 |\n", "| time_elapsed | 2259 |\n", "| total_timesteps | 421000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0304 |\n", "| value_loss | 0.00153 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84300 |\n", "| time_elapsed | 2262 |\n", "| total_timesteps | 421500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0346 |\n", "| value_loss | 0.00164 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84400 |\n", "| time_elapsed | 2265 |\n", "| total_timesteps | 422000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84500 |\n", "| time_elapsed | 2267 |\n", "| total_timesteps | 422500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0546 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84600 |\n", "| time_elapsed | 2270 |\n", "| total_timesteps | 423000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84700 |\n", "| time_elapsed | 2273 |\n", "| total_timesteps | 423500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0352 |\n", "| value_loss | 0.00185 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84800 |\n", "| time_elapsed | 2275 |\n", "| total_timesteps | 424000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.049 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 84900 |\n", "| time_elapsed | 2278 |\n", "| total_timesteps | 424500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85000 |\n", "| time_elapsed | 2281 |\n", "| total_timesteps | 425000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.932 |\n", "| value_loss | 0.884 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85100 |\n", "| time_elapsed | 2283 |\n", "| total_timesteps | 425500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.061 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85200 |\n", "| time_elapsed | 2286 |\n", "| total_timesteps | 426000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0679 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85300 |\n", "| time_elapsed | 2289 |\n", "| total_timesteps | 426500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85400 |\n", "| time_elapsed | 2291 |\n", "| total_timesteps | 427000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85500 |\n", "| time_elapsed | 2294 |\n", "| total_timesteps | 427500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85600 |\n", "| time_elapsed | 2297 |\n", "| total_timesteps | 428000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00223 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85700 |\n", "| time_elapsed | 2299 |\n", "| total_timesteps | 428500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85800 |\n", "| time_elapsed | 2302 |\n", "| total_timesteps | 429000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0724 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 85900 |\n", "| time_elapsed | 2305 |\n", "| total_timesteps | 429500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86000 |\n", "| time_elapsed | 2307 |\n", "| total_timesteps | 430000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0649 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86100 |\n", "| time_elapsed | 2310 |\n", "| total_timesteps | 430500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86200 |\n", "| time_elapsed | 2313 |\n", "| total_timesteps | 431000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0599 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86300 |\n", "| time_elapsed | 2315 |\n", "| total_timesteps | 431500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86400 |\n", "| time_elapsed | 2318 |\n", "| total_timesteps | 432000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0539 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86500 |\n", "| time_elapsed | 2320 |\n", "| total_timesteps | 432500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0543 |\n", "| value_loss | 0.00208 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86600 |\n", "| time_elapsed | 2323 |\n", "| total_timesteps | 433000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0396 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86700 |\n", "| time_elapsed | 2326 |\n", "| total_timesteps | 433500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0556 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86800 |\n", "| time_elapsed | 2328 |\n", "| total_timesteps | 434000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.053 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 86900 |\n", "| time_elapsed | 2331 |\n", "| total_timesteps | 434500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87000 |\n", "| time_elapsed | 2334 |\n", "| total_timesteps | 435000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87100 |\n", "| time_elapsed | 2336 |\n", "| total_timesteps | 435500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.241 |\n", "| value_loss | 0.322 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87200 |\n", "| time_elapsed | 2339 |\n", "| total_timesteps | 436000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0427 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87300 |\n", "| time_elapsed | 2342 |\n", "| total_timesteps | 436500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.23 |\n", "| value_loss | 1.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87400 |\n", "| time_elapsed | 2344 |\n", "| total_timesteps | 437000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87500 |\n", "| time_elapsed | 2347 |\n", "| total_timesteps | 437500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87600 |\n", "| time_elapsed | 2350 |\n", "| total_timesteps | 438000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0338 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87700 |\n", "| time_elapsed | 2352 |\n", "| total_timesteps | 438500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.96 |\n", "| value_loss | 0.888 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87800 |\n", "| time_elapsed | 2355 |\n", "| total_timesteps | 439000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0649 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 87900 |\n", "| time_elapsed | 2358 |\n", "| total_timesteps | 439500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.535 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88000 |\n", "| time_elapsed | 2360 |\n", "| total_timesteps | 440000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.2 |\n", "| value_loss | 2 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88100 |\n", "| time_elapsed | 2363 |\n", "| total_timesteps | 440500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0391 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88200 |\n", "| time_elapsed | 2366 |\n", "| total_timesteps | 441000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0645 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88300 |\n", "| time_elapsed | 2368 |\n", "| total_timesteps | 441500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88400 |\n", "| time_elapsed | 2371 |\n", "| total_timesteps | 442000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0377 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88500 |\n", "| time_elapsed | 2373 |\n", "| total_timesteps | 442500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88600 |\n", "| time_elapsed | 2376 |\n", "| total_timesteps | 443000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0641 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88700 |\n", "| time_elapsed | 2379 |\n", "| total_timesteps | 443500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0621 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88800 |\n", "| time_elapsed | 2381 |\n", "| total_timesteps | 444000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 88900 |\n", "| time_elapsed | 2384 |\n", "| total_timesteps | 444500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89000 |\n", "| time_elapsed | 2387 |\n", "| total_timesteps | 445000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00206 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89100 |\n", "| time_elapsed | 2389 |\n", "| total_timesteps | 445500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89200 |\n", "| time_elapsed | 2392 |\n", "| total_timesteps | 446000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0337 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89300 |\n", "| time_elapsed | 2395 |\n", "| total_timesteps | 446500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0556 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89400 |\n", "| time_elapsed | 2397 |\n", "| total_timesteps | 447000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89500 |\n", "| time_elapsed | 2400 |\n", "| total_timesteps | 447500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89600 |\n", "| time_elapsed | 2403 |\n", "| total_timesteps | 448000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89700 |\n", "| time_elapsed | 2405 |\n", "| total_timesteps | 448500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89800 |\n", "| time_elapsed | 2408 |\n", "| total_timesteps | 449000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 89900 |\n", "| time_elapsed | 2411 |\n", "| total_timesteps | 449500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "Eval num_timesteps=450000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 450000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0508 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90000 |\n", "| time_elapsed | 2424 |\n", "| total_timesteps | 450000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90100 |\n", "| time_elapsed | 2427 |\n", "| total_timesteps | 450500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0297 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90200 |\n", "| time_elapsed | 2429 |\n", "| total_timesteps | 451000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0686 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90300 |\n", "| time_elapsed | 2432 |\n", "| total_timesteps | 451500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0807 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90400 |\n", "| time_elapsed | 2435 |\n", "| total_timesteps | 452000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0821 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90500 |\n", "| time_elapsed | 2437 |\n", "| total_timesteps | 452500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0372 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90600 |\n", "| time_elapsed | 2440 |\n", "| total_timesteps | 453000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90700 |\n", "| time_elapsed | 2443 |\n", "| total_timesteps | 453500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.036 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90800 |\n", "| time_elapsed | 2445 |\n", "| total_timesteps | 454000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 90900 |\n", "| time_elapsed | 2448 |\n", "| total_timesteps | 454500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0338 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91000 |\n", "| time_elapsed | 2451 |\n", "| total_timesteps | 455000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91100 |\n", "| time_elapsed | 2453 |\n", "| total_timesteps | 455500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0599 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91200 |\n", "| time_elapsed | 2456 |\n", "| total_timesteps | 456000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.476 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91300 |\n", "| time_elapsed | 2458 |\n", "| total_timesteps | 456500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0557 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91400 |\n", "| time_elapsed | 2461 |\n", "| total_timesteps | 457000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91500 |\n", "| time_elapsed | 2464 |\n", "| total_timesteps | 457500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0714 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91600 |\n", "| time_elapsed | 2466 |\n", "| total_timesteps | 458000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91700 |\n", "| time_elapsed | 2469 |\n", "| total_timesteps | 458500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91800 |\n", "| time_elapsed | 2472 |\n", "| total_timesteps | 459000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.049 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 91900 |\n", "| time_elapsed | 2474 |\n", "| total_timesteps | 459500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00203 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92000 |\n", "| time_elapsed | 2477 |\n", "| total_timesteps | 460000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.24 |\n", "| value_loss | 1.26 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92100 |\n", "| time_elapsed | 2480 |\n", "| total_timesteps | 460500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0695 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92200 |\n", "| time_elapsed | 2482 |\n", "| total_timesteps | 461000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92300 |\n", "| time_elapsed | 2485 |\n", "| total_timesteps | 461500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92400 |\n", "| time_elapsed | 2488 |\n", "| total_timesteps | 462000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92500 |\n", "| time_elapsed | 2490 |\n", "| total_timesteps | 462500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.84 |\n", "| value_loss | 0.705 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92600 |\n", "| time_elapsed | 2493 |\n", "| total_timesteps | 463000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.035 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92700 |\n", "| time_elapsed | 2495 |\n", "| total_timesteps | 463500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92800 |\n", "| time_elapsed | 2498 |\n", "| total_timesteps | 464000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0556 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 92900 |\n", "| time_elapsed | 2501 |\n", "| total_timesteps | 464500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0329 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93000 |\n", "| time_elapsed | 2503 |\n", "| total_timesteps | 465000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0489 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93100 |\n", "| time_elapsed | 2506 |\n", "| total_timesteps | 465500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.353 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93200 |\n", "| time_elapsed | 2509 |\n", "| total_timesteps | 466000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93300 |\n", "| time_elapsed | 2511 |\n", "| total_timesteps | 466500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.00198 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93400 |\n", "| time_elapsed | 2514 |\n", "| total_timesteps | 467000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93500 |\n", "| time_elapsed | 2517 |\n", "| total_timesteps | 467500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.056 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93600 |\n", "| time_elapsed | 2519 |\n", "| total_timesteps | 468000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93700 |\n", "| time_elapsed | 2522 |\n", "| total_timesteps | 468500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93800 |\n", "| time_elapsed | 2525 |\n", "| total_timesteps | 469000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.07 |\n", "| value_loss | 0.00211 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 93900 |\n", "| time_elapsed | 2527 |\n", "| total_timesteps | 469500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94000 |\n", "| time_elapsed | 2530 |\n", "| total_timesteps | 470000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0845 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94100 |\n", "| time_elapsed | 2533 |\n", "| total_timesteps | 470500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.771 |\n", "| value_loss | 0.396 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94200 |\n", "| time_elapsed | 2535 |\n", "| total_timesteps | 471000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0884 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94300 |\n", "| time_elapsed | 2538 |\n", "| total_timesteps | 471500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.27 |\n", "| value_loss | 1.11 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94400 |\n", "| time_elapsed | 2540 |\n", "| total_timesteps | 472000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94500 |\n", "| time_elapsed | 2543 |\n", "| total_timesteps | 472500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94600 |\n", "| time_elapsed | 2546 |\n", "| total_timesteps | 473000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94700 |\n", "| time_elapsed | 2549 |\n", "| total_timesteps | 473500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.07 |\n", "| value_loss | 0.711 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94800 |\n", "| time_elapsed | 2551 |\n", "| total_timesteps | 474000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.12 |\n", "| value_loss | 0.916 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 94900 |\n", "| time_elapsed | 2554 |\n", "| total_timesteps | 474500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.028 |\n", "| value_loss | 0.00157 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95000 |\n", "| time_elapsed | 2556 |\n", "| total_timesteps | 475000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0349 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95100 |\n", "| time_elapsed | 2559 |\n", "| total_timesteps | 475500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.898 |\n", "| value_loss | 0.712 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95200 |\n", "| time_elapsed | 2562 |\n", "| total_timesteps | 476000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95300 |\n", "| time_elapsed | 2564 |\n", "| total_timesteps | 476500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95400 |\n", "| time_elapsed | 2567 |\n", "| total_timesteps | 477000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0355 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95500 |\n", "| time_elapsed | 2570 |\n", "| total_timesteps | 477500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95600 |\n", "| time_elapsed | 2572 |\n", "| total_timesteps | 478000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95700 |\n", "| time_elapsed | 2575 |\n", "| total_timesteps | 478500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.764 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95800 |\n", "| time_elapsed | 2578 |\n", "| total_timesteps | 479000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 95900 |\n", "| time_elapsed | 2581 |\n", "| total_timesteps | 479500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0733 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96000 |\n", "| time_elapsed | 2583 |\n", "| total_timesteps | 480000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0405 |\n", "| value_loss | 0.00185 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96100 |\n", "| time_elapsed | 2586 |\n", "| total_timesteps | 480500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0269 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96200 |\n", "| time_elapsed | 2588 |\n", "| total_timesteps | 481000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0406 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96300 |\n", "| time_elapsed | 2591 |\n", "| total_timesteps | 481500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96400 |\n", "| time_elapsed | 2594 |\n", "| total_timesteps | 482000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0544 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96500 |\n", "| time_elapsed | 2596 |\n", "| total_timesteps | 482500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96600 |\n", "| time_elapsed | 2599 |\n", "| total_timesteps | 483000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0331 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96700 |\n", "| time_elapsed | 2601 |\n", "| total_timesteps | 483500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96800 |\n", "| time_elapsed | 2604 |\n", "| total_timesteps | 484000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0309 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 96900 |\n", "| time_elapsed | 2607 |\n", "| total_timesteps | 484500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0381 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97000 |\n", "| time_elapsed | 2609 |\n", "| total_timesteps | 485000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0623 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97100 |\n", "| time_elapsed | 2612 |\n", "| total_timesteps | 485500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97200 |\n", "| time_elapsed | 2615 |\n", "| total_timesteps | 486000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0344 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97300 |\n", "| time_elapsed | 2617 |\n", "| total_timesteps | 486500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97400 |\n", "| time_elapsed | 2620 |\n", "| total_timesteps | 487000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0375 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97500 |\n", "| time_elapsed | 2623 |\n", "| total_timesteps | 487500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97600 |\n", "| time_elapsed | 2625 |\n", "| total_timesteps | 488000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97700 |\n", "| time_elapsed | 2628 |\n", "| total_timesteps | 488500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0489 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97800 |\n", "| time_elapsed | 2631 |\n", "| total_timesteps | 489000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0613 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 97900 |\n", "| time_elapsed | 2633 |\n", "| total_timesteps | 489500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.048 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98000 |\n", "| time_elapsed | 2636 |\n", "| total_timesteps | 490000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 0.889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98100 |\n", "| time_elapsed | 2639 |\n", "| total_timesteps | 490500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.03 |\n", "| value_loss | 2.01 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98200 |\n", "| time_elapsed | 2642 |\n", "| total_timesteps | 491000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.738 |\n", "| value_loss | 0.711 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98300 |\n", "| time_elapsed | 2644 |\n", "| total_timesteps | 491500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.51 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98400 |\n", "| time_elapsed | 2647 |\n", "| total_timesteps | 492000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.01 |\n", "| value_loss | 0.71 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98500 |\n", "| time_elapsed | 2650 |\n", "| total_timesteps | 492500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98600 |\n", "| time_elapsed | 2652 |\n", "| total_timesteps | 493000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98700 |\n", "| time_elapsed | 2655 |\n", "| total_timesteps | 493500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.627 |\n", "| value_loss | 0.709 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98800 |\n", "| time_elapsed | 2658 |\n", "| total_timesteps | 494000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 98900 |\n", "| time_elapsed | 2660 |\n", "| total_timesteps | 494500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.08 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99000 |\n", "| time_elapsed | 2663 |\n", "| total_timesteps | 495000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00187 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99100 |\n", "| time_elapsed | 2666 |\n", "| total_timesteps | 495500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99200 |\n", "| time_elapsed | 2668 |\n", "| total_timesteps | 496000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.048 |\n", "| value_loss | 0.00156 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99300 |\n", "| time_elapsed | 2671 |\n", "| total_timesteps | 496500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0247 |\n", "| value_loss | 0.00155 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99400 |\n", "| time_elapsed | 2674 |\n", "| total_timesteps | 497000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99500 |\n", "| time_elapsed | 2676 |\n", "| total_timesteps | 497500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0611 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99600 |\n", "| time_elapsed | 2679 |\n", "| total_timesteps | 498000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0636 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99700 |\n", "| time_elapsed | 2682 |\n", "| total_timesteps | 498500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99800 |\n", "| time_elapsed | 2684 |\n", "| total_timesteps | 499000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.059 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 99900 |\n", "| time_elapsed | 2687 |\n", "| total_timesteps | 499500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100000 |\n", "| time_elapsed | 2690 |\n", "| total_timesteps | 500000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0405 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100100 |\n", "| time_elapsed | 2692 |\n", "| total_timesteps | 500500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100200 |\n", "| time_elapsed | 2695 |\n", "| total_timesteps | 501000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100300 |\n", "| time_elapsed | 2698 |\n", "| total_timesteps | 501500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0257 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100400 |\n", "| time_elapsed | 2700 |\n", "| total_timesteps | 502000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100500 |\n", "| time_elapsed | 2703 |\n", "| total_timesteps | 502500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0656 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100600 |\n", "| time_elapsed | 2706 |\n", "| total_timesteps | 503000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0395 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100700 |\n", "| time_elapsed | 2708 |\n", "| total_timesteps | 503500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0286 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 516 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100800 |\n", "| time_elapsed | 2711 |\n", "| total_timesteps | 504000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0368 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 100900 |\n", "| time_elapsed | 2714 |\n", "| total_timesteps | 504500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101000 |\n", "| time_elapsed | 2716 |\n", "| total_timesteps | 505000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.115 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101100 |\n", "| time_elapsed | 2719 |\n", "| total_timesteps | 505500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0327 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 513 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101200 |\n", "| time_elapsed | 2722 |\n", "| total_timesteps | 506000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.083 |\n", "| value_loss | 0.00238 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101300 |\n", "| time_elapsed | 2724 |\n", "| total_timesteps | 506500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 514 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101400 |\n", "| time_elapsed | 2727 |\n", "| total_timesteps | 507000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0788 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101500 |\n", "| time_elapsed | 2729 |\n", "| total_timesteps | 507500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0727 |\n", "| value_loss | 0.00238 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 515 |\n", "| ep_rew_mean | 16.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101600 |\n", "| time_elapsed | 2732 |\n", "| total_timesteps | 508000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.5 |\n", "| value_loss | 0.877 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101700 |\n", "| time_elapsed | 2735 |\n", "| total_timesteps | 508500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0596 |\n", "| value_loss | 0.00229 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 516 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101800 |\n", "| time_elapsed | 2737 |\n", "| total_timesteps | 509000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0299 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 101900 |\n", "| time_elapsed | 2740 |\n", "| total_timesteps | 509500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102000 |\n", "| time_elapsed | 2743 |\n", "| total_timesteps | 510000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 1.26 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102100 |\n", "| time_elapsed | 2745 |\n", "| total_timesteps | 510500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.999 |\n", "| value_loss | 0.883 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102200 |\n", "| time_elapsed | 2748 |\n", "| total_timesteps | 511000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0624 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102300 |\n", "| time_elapsed | 2751 |\n", "| total_timesteps | 511500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102400 |\n", "| time_elapsed | 2753 |\n", "| total_timesteps | 512000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0483 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102500 |\n", "| time_elapsed | 2756 |\n", "| total_timesteps | 512500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102600 |\n", "| time_elapsed | 2759 |\n", "| total_timesteps | 513000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102700 |\n", "| time_elapsed | 2761 |\n", "| total_timesteps | 513500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0327 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102800 |\n", "| time_elapsed | 2764 |\n", "| total_timesteps | 514000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 102900 |\n", "| time_elapsed | 2767 |\n", "| total_timesteps | 514500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.601 |\n", "| value_loss | 0.524 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103000 |\n", "| time_elapsed | 2769 |\n", "| total_timesteps | 515000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103100 |\n", "| time_elapsed | 2772 |\n", "| total_timesteps | 515500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00207 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103200 |\n", "| time_elapsed | 2775 |\n", "| total_timesteps | 516000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0299 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103300 |\n", "| time_elapsed | 2777 |\n", "| total_timesteps | 516500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.198 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103400 |\n", "| time_elapsed | 2780 |\n", "| total_timesteps | 517000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0437 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103500 |\n", "| time_elapsed | 2782 |\n", "| total_timesteps | 517500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.482 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103600 |\n", "| time_elapsed | 2785 |\n", "| total_timesteps | 518000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0612 |\n", "| value_loss | 0.00235 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103700 |\n", "| time_elapsed | 2788 |\n", "| total_timesteps | 518500 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0517 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103800 |\n", "| time_elapsed | 2790 |\n", "| total_timesteps | 519000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0291 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 103900 |\n", "| time_elapsed | 2793 |\n", "| total_timesteps | 519500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0344 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104000 |\n", "| time_elapsed | 2796 |\n", "| total_timesteps | 520000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104100 |\n", "| time_elapsed | 2798 |\n", "| total_timesteps | 520500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0347 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104200 |\n", "| time_elapsed | 2801 |\n", "| total_timesteps | 521000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0302 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104300 |\n", "| time_elapsed | 2804 |\n", "| total_timesteps | 521500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.0022 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104400 |\n", "| time_elapsed | 2806 |\n", "| total_timesteps | 522000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104500 |\n", "| time_elapsed | 2809 |\n", "| total_timesteps | 522500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 516 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104600 |\n", "| time_elapsed | 2812 |\n", "| total_timesteps | 523000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0518 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104700 |\n", "| time_elapsed | 2814 |\n", "| total_timesteps | 523500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 516 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104800 |\n", "| time_elapsed | 2817 |\n", "| total_timesteps | 524000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 104900 |\n", "| time_elapsed | 2820 |\n", "| total_timesteps | 524500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0628 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "Eval num_timesteps=525000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 525000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.06 |\n", "| value_loss | 0.705 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105000 |\n", "| time_elapsed | 2833 |\n", "| total_timesteps | 525000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 517 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105100 |\n", "| time_elapsed | 2836 |\n", "| total_timesteps | 525500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0346 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105200 |\n", "| time_elapsed | 2838 |\n", "| total_timesteps | 526000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0681 |\n", "| value_loss | 0.00169 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105300 |\n", "| time_elapsed | 2841 |\n", "| total_timesteps | 526500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105400 |\n", "| time_elapsed | 2843 |\n", "| total_timesteps | 527000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105500 |\n", "| time_elapsed | 2846 |\n", "| total_timesteps | 527500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.226 |\n", "| value_loss | 0.33 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105600 |\n", "| time_elapsed | 2849 |\n", "| total_timesteps | 528000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105700 |\n", "| time_elapsed | 2851 |\n", "| total_timesteps | 528500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00208 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105800 |\n", "| time_elapsed | 2854 |\n", "| total_timesteps | 529000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0798 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 105900 |\n", "| time_elapsed | 2857 |\n", "| total_timesteps | 529500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106000 |\n", "| time_elapsed | 2859 |\n", "| total_timesteps | 530000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106100 |\n", "| time_elapsed | 2862 |\n", "| total_timesteps | 530500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.00204 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106200 |\n", "| time_elapsed | 2865 |\n", "| total_timesteps | 531000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106300 |\n", "| time_elapsed | 2867 |\n", "| total_timesteps | 531500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106400 |\n", "| time_elapsed | 2870 |\n", "| total_timesteps | 532000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.496 |\n", "| value_loss | 0.522 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106500 |\n", "| time_elapsed | 2872 |\n", "| total_timesteps | 532500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0517 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106600 |\n", "| time_elapsed | 2875 |\n", "| total_timesteps | 533000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0547 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106700 |\n", "| time_elapsed | 2878 |\n", "| total_timesteps | 533500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106800 |\n", "| time_elapsed | 2880 |\n", "| total_timesteps | 534000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 106900 |\n", "| time_elapsed | 2883 |\n", "| total_timesteps | 534500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.97 |\n", "| value_loss | 0.703 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107000 |\n", "| time_elapsed | 2886 |\n", "| total_timesteps | 535000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00206 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107100 |\n", "| time_elapsed | 2888 |\n", "| total_timesteps | 535500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.91 |\n", "| value_loss | 0.704 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107200 |\n", "| time_elapsed | 2891 |\n", "| total_timesteps | 536000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107300 |\n", "| time_elapsed | 2894 |\n", "| total_timesteps | 536500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.9 |\n", "| value_loss | 0.704 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107400 |\n", "| time_elapsed | 2897 |\n", "| total_timesteps | 537000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107500 |\n", "| time_elapsed | 2899 |\n", "| total_timesteps | 537500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00186 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107600 |\n", "| time_elapsed | 2902 |\n", "| total_timesteps | 538000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.08 |\n", "| value_loss | 0.887 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107700 |\n", "| time_elapsed | 2904 |\n", "| total_timesteps | 538500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.699 |\n", "| value_loss | 0.53 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107800 |\n", "| time_elapsed | 2907 |\n", "| total_timesteps | 539000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.874 |\n", "| value_loss | 0.889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 107900 |\n", "| time_elapsed | 2910 |\n", "| total_timesteps | 539500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.00167 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108000 |\n", "| time_elapsed | 2912 |\n", "| total_timesteps | 540000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.662 |\n", "| value_loss | 0.532 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108100 |\n", "| time_elapsed | 2915 |\n", "| total_timesteps | 540500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00161 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108200 |\n", "| time_elapsed | 2917 |\n", "| total_timesteps | 541000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.27 |\n", "| value_loss | 0.889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108300 |\n", "| time_elapsed | 2920 |\n", "| total_timesteps | 541500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108400 |\n", "| time_elapsed | 2923 |\n", "| total_timesteps | 542000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 1.67 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108500 |\n", "| time_elapsed | 2925 |\n", "| total_timesteps | 542500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0515 |\n", "| value_loss | 0.00159 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108600 |\n", "| time_elapsed | 2928 |\n", "| total_timesteps | 543000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00166 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108700 |\n", "| time_elapsed | 2930 |\n", "| total_timesteps | 543500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.993 |\n", "| value_loss | 0.71 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108800 |\n", "| time_elapsed | 2933 |\n", "| total_timesteps | 544000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 108900 |\n", "| time_elapsed | 2936 |\n", "| total_timesteps | 544500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.18 |\n", "| value_loss | 0.177 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109000 |\n", "| time_elapsed | 2938 |\n", "| total_timesteps | 545000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109100 |\n", "| time_elapsed | 2941 |\n", "| total_timesteps | 545500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.22 |\n", "| value_loss | 0.891 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109200 |\n", "| time_elapsed | 2944 |\n", "| total_timesteps | 546000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109300 |\n", "| time_elapsed | 2946 |\n", "| total_timesteps | 546500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0635 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109400 |\n", "| time_elapsed | 2949 |\n", "| total_timesteps | 547000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.898 |\n", "| value_loss | 0.71 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109500 |\n", "| time_elapsed | 2952 |\n", "| total_timesteps | 547500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109600 |\n", "| time_elapsed | 2954 |\n", "| total_timesteps | 548000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0548 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109700 |\n", "| time_elapsed | 2957 |\n", "| total_timesteps | 548500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0545 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109800 |\n", "| time_elapsed | 2960 |\n", "| total_timesteps | 549000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0416 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 109900 |\n", "| time_elapsed | 2962 |\n", "| total_timesteps | 549500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110000 |\n", "| time_elapsed | 2965 |\n", "| total_timesteps | 550000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0488 |\n", "| value_loss | 0.00163 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110100 |\n", "| time_elapsed | 2968 |\n", "| total_timesteps | 550500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0862 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110200 |\n", "| time_elapsed | 2970 |\n", "| total_timesteps | 551000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110300 |\n", "| time_elapsed | 2973 |\n", "| total_timesteps | 551500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110400 |\n", "| time_elapsed | 2975 |\n", "| total_timesteps | 552000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110500 |\n", "| time_elapsed | 2978 |\n", "| total_timesteps | 552500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110600 |\n", "| time_elapsed | 2981 |\n", "| total_timesteps | 553000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110700 |\n", "| time_elapsed | 2983 |\n", "| total_timesteps | 553500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110800 |\n", "| time_elapsed | 2986 |\n", "| total_timesteps | 554000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0554 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 110900 |\n", "| time_elapsed | 2989 |\n", "| total_timesteps | 554500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0519 |\n", "| value_loss | 0.00164 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111000 |\n", "| time_elapsed | 2992 |\n", "| total_timesteps | 555000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.0019 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111100 |\n", "| time_elapsed | 2994 |\n", "| total_timesteps | 555500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.813 |\n", "| value_loss | 0.528 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111200 |\n", "| time_elapsed | 2997 |\n", "| total_timesteps | 556000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0634 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111300 |\n", "| time_elapsed | 2999 |\n", "| total_timesteps | 556500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111400 |\n", "| time_elapsed | 3002 |\n", "| total_timesteps | 557000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111500 |\n", "| time_elapsed | 3005 |\n", "| total_timesteps | 557500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111600 |\n", "| time_elapsed | 3007 |\n", "| total_timesteps | 558000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111700 |\n", "| time_elapsed | 3010 |\n", "| total_timesteps | 558500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.8 |\n", "| value_loss | 2.01 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111800 |\n", "| time_elapsed | 3013 |\n", "| total_timesteps | 559000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0486 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 111900 |\n", "| time_elapsed | 3015 |\n", "| total_timesteps | 559500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112000 |\n", "| time_elapsed | 3018 |\n", "| total_timesteps | 560000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.048 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112100 |\n", "| time_elapsed | 3021 |\n", "| total_timesteps | 560500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.83 |\n", "| value_loss | 2.57 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112200 |\n", "| time_elapsed | 3023 |\n", "| total_timesteps | 561000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0595 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112300 |\n", "| time_elapsed | 3026 |\n", "| total_timesteps | 561500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.32 |\n", "| value_loss | 2.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112400 |\n", "| time_elapsed | 3028 |\n", "| total_timesteps | 562000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112500 |\n", "| time_elapsed | 3031 |\n", "| total_timesteps | 562500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112600 |\n", "| time_elapsed | 3034 |\n", "| total_timesteps | 563000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0655 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112700 |\n", "| time_elapsed | 3036 |\n", "| total_timesteps | 563500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00179 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 518 |\n", "| ep_rew_mean | 17 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112800 |\n", "| time_elapsed | 3039 |\n", "| total_timesteps | 564000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 112900 |\n", "| time_elapsed | 3042 |\n", "| total_timesteps | 564500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0604 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113000 |\n", "| time_elapsed | 3044 |\n", "| total_timesteps | 565000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00207 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113100 |\n", "| time_elapsed | 3047 |\n", "| total_timesteps | 565500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.133 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113200 |\n", "| time_elapsed | 3050 |\n", "| total_timesteps | 566000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113300 |\n", "| time_elapsed | 3052 |\n", "| total_timesteps | 566500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0628 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113400 |\n", "| time_elapsed | 3055 |\n", "| total_timesteps | 567000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0391 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113500 |\n", "| time_elapsed | 3058 |\n", "| total_timesteps | 567500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113600 |\n", "| time_elapsed | 3060 |\n", "| total_timesteps | 568000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113700 |\n", "| time_elapsed | 3063 |\n", "| total_timesteps | 568500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.307 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113800 |\n", "| time_elapsed | 3066 |\n", "| total_timesteps | 569000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 113900 |\n", "| time_elapsed | 3068 |\n", "| total_timesteps | 569500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0584 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114000 |\n", "| time_elapsed | 3071 |\n", "| total_timesteps | 570000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.064 |\n", "| value_loss | 0.00208 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114100 |\n", "| time_elapsed | 3074 |\n", "| total_timesteps | 570500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00224 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114200 |\n", "| time_elapsed | 3076 |\n", "| total_timesteps | 571000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114300 |\n", "| time_elapsed | 3079 |\n", "| total_timesteps | 571500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0835 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114400 |\n", "| time_elapsed | 3082 |\n", "| total_timesteps | 572000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0588 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114500 |\n", "| time_elapsed | 3084 |\n", "| total_timesteps | 572500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0629 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114600 |\n", "| time_elapsed | 3087 |\n", "| total_timesteps | 573000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.745 |\n", "| value_loss | 0.702 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114700 |\n", "| time_elapsed | 3090 |\n", "| total_timesteps | 573500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114800 |\n", "| time_elapsed | 3092 |\n", "| total_timesteps | 574000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 114900 |\n", "| time_elapsed | 3095 |\n", "| total_timesteps | 574500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0412 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115000 |\n", "| time_elapsed | 3098 |\n", "| total_timesteps | 575000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00187 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115100 |\n", "| time_elapsed | 3100 |\n", "| total_timesteps | 575500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.00191 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115200 |\n", "| time_elapsed | 3103 |\n", "| total_timesteps | 576000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0403 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115300 |\n", "| time_elapsed | 3106 |\n", "| total_timesteps | 576500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115400 |\n", "| time_elapsed | 3108 |\n", "| total_timesteps | 577000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115500 |\n", "| time_elapsed | 3111 |\n", "| total_timesteps | 577500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115600 |\n", "| time_elapsed | 3114 |\n", "| total_timesteps | 578000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115700 |\n", "| time_elapsed | 3116 |\n", "| total_timesteps | 578500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115800 |\n", "| time_elapsed | 3119 |\n", "| total_timesteps | 579000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 115900 |\n", "| time_elapsed | 3122 |\n", "| total_timesteps | 579500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0602 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116000 |\n", "| time_elapsed | 3124 |\n", "| total_timesteps | 580000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0537 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116100 |\n", "| time_elapsed | 3127 |\n", "| total_timesteps | 580500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0498 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116200 |\n", "| time_elapsed | 3130 |\n", "| total_timesteps | 581000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116300 |\n", "| time_elapsed | 3132 |\n", "| total_timesteps | 581500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0441 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116400 |\n", "| time_elapsed | 3135 |\n", "| total_timesteps | 582000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116500 |\n", "| time_elapsed | 3138 |\n", "| total_timesteps | 582500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0523 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116600 |\n", "| time_elapsed | 3140 |\n", "| total_timesteps | 583000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0558 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116700 |\n", "| time_elapsed | 3143 |\n", "| total_timesteps | 583500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0659 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116800 |\n", "| time_elapsed | 3146 |\n", "| total_timesteps | 584000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0598 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 116900 |\n", "| time_elapsed | 3148 |\n", "| total_timesteps | 584500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117000 |\n", "| time_elapsed | 3151 |\n", "| total_timesteps | 585000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00201 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117100 |\n", "| time_elapsed | 3154 |\n", "| total_timesteps | 585500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0412 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117200 |\n", "| time_elapsed | 3156 |\n", "| total_timesteps | 586000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.00186 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117300 |\n", "| time_elapsed | 3159 |\n", "| total_timesteps | 586500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117400 |\n", "| time_elapsed | 3162 |\n", "| total_timesteps | 587000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117500 |\n", "| time_elapsed | 3164 |\n", "| total_timesteps | 587500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0661 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117600 |\n", "| time_elapsed | 3167 |\n", "| total_timesteps | 588000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117700 |\n", "| time_elapsed | 3170 |\n", "| total_timesteps | 588500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117800 |\n", "| time_elapsed | 3173 |\n", "| total_timesteps | 589000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0505 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 117900 |\n", "| time_elapsed | 3175 |\n", "| total_timesteps | 589500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.19 |\n", "| value_loss | 0.885 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118000 |\n", "| time_elapsed | 3178 |\n", "| total_timesteps | 590000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0512 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118100 |\n", "| time_elapsed | 3181 |\n", "| total_timesteps | 590500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.15 |\n", "| value_loss | 1.49 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118200 |\n", "| time_elapsed | 3184 |\n", "| total_timesteps | 591000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.83 |\n", "| value_loss | 2 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118300 |\n", "| time_elapsed | 3186 |\n", "| total_timesteps | 591500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00178 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118400 |\n", "| time_elapsed | 3189 |\n", "| total_timesteps | 592000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0521 |\n", "| value_loss | 0.00192 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118500 |\n", "| time_elapsed | 3192 |\n", "| total_timesteps | 592500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0616 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118600 |\n", "| time_elapsed | 3194 |\n", "| total_timesteps | 593000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0349 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118700 |\n", "| time_elapsed | 3197 |\n", "| total_timesteps | 593500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0458 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118800 |\n", "| time_elapsed | 3200 |\n", "| total_timesteps | 594000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 118900 |\n", "| time_elapsed | 3202 |\n", "| total_timesteps | 594500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0518 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119000 |\n", "| time_elapsed | 3205 |\n", "| total_timesteps | 595000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0483 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119100 |\n", "| time_elapsed | 3208 |\n", "| total_timesteps | 595500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0461 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119200 |\n", "| time_elapsed | 3210 |\n", "| total_timesteps | 596000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.763 |\n", "| value_loss | 0.71 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119300 |\n", "| time_elapsed | 3213 |\n", "| total_timesteps | 596500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.718 |\n", "| value_loss | 0.531 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119400 |\n", "| time_elapsed | 3216 |\n", "| total_timesteps | 597000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119500 |\n", "| time_elapsed | 3218 |\n", "| total_timesteps | 597500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119600 |\n", "| time_elapsed | 3221 |\n", "| total_timesteps | 598000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119700 |\n", "| time_elapsed | 3223 |\n", "| total_timesteps | 598500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119800 |\n", "| time_elapsed | 3226 |\n", "| total_timesteps | 599000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 119900 |\n", "| time_elapsed | 3229 |\n", "| total_timesteps | 599500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.037 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "Eval num_timesteps=600000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 600000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0539 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120000 |\n", "| time_elapsed | 3243 |\n", "| total_timesteps | 600000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120100 |\n", "| time_elapsed | 3245 |\n", "| total_timesteps | 600500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.24 |\n", "| value_loss | 0.344 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120200 |\n", "| time_elapsed | 3248 |\n", "| total_timesteps | 601000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.00286 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120300 |\n", "| time_elapsed | 3251 |\n", "| total_timesteps | 601500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00292 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120400 |\n", "| time_elapsed | 3253 |\n", "| total_timesteps | 602000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120500 |\n", "| time_elapsed | 3256 |\n", "| total_timesteps | 602500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.794 |\n", "| value_loss | 0.512 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 120600 |\n", "| time_elapsed | 3259 |\n", "| total_timesteps | 603000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.363 |\n", "| value_loss | 0.17 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 120700 |\n", "| time_elapsed | 3262 |\n", "| total_timesteps | 603500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0784 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 120800 |\n", "| time_elapsed | 3264 |\n", "| total_timesteps | 604000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.219 |\n", "| value_loss | 0.342 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 120900 |\n", "| time_elapsed | 3267 |\n", "| total_timesteps | 604500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.92 |\n", "| value_loss | 2.54 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121000 |\n", "| time_elapsed | 3270 |\n", "| total_timesteps | 605000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0618 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121100 |\n", "| time_elapsed | 3273 |\n", "| total_timesteps | 605500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0634 |\n", "| value_loss | 0.00285 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121200 |\n", "| time_elapsed | 3275 |\n", "| total_timesteps | 606000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121300 |\n", "| time_elapsed | 3278 |\n", "| total_timesteps | 606500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0947 |\n", "| value_loss | 0.172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121400 |\n", "| time_elapsed | 3281 |\n", "| total_timesteps | 607000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0803 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121500 |\n", "| time_elapsed | 3283 |\n", "| total_timesteps | 607500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.333 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121600 |\n", "| time_elapsed | 3286 |\n", "| total_timesteps | 608000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0376 |\n", "| value_loss | 0.00259 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 121700 |\n", "| time_elapsed | 3289 |\n", "| total_timesteps | 608500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0363 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 121800 |\n", "| time_elapsed | 3291 |\n", "| total_timesteps | 609000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0727 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 121900 |\n", "| time_elapsed | 3294 |\n", "| total_timesteps | 609500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.487 |\n", "| value_loss | 0.52 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 122000 |\n", "| time_elapsed | 3297 |\n", "| total_timesteps | 610000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0349 |\n", "| value_loss | 0.00232 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122100 |\n", "| time_elapsed | 3300 |\n", "| total_timesteps | 610500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122200 |\n", "| time_elapsed | 3302 |\n", "| total_timesteps | 611000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0688 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122300 |\n", "| time_elapsed | 3305 |\n", "| total_timesteps | 611500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 122400 |\n", "| time_elapsed | 3308 |\n", "| total_timesteps | 612000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0588 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 122500 |\n", "| time_elapsed | 3310 |\n", "| total_timesteps | 612500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 122600 |\n", "| time_elapsed | 3313 |\n", "| total_timesteps | 613000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0856 |\n", "| value_loss | 0.00231 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122700 |\n", "| time_elapsed | 3316 |\n", "| total_timesteps | 613500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122800 |\n", "| time_elapsed | 3318 |\n", "| total_timesteps | 614000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0453 |\n", "| value_loss | 0.00234 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 122900 |\n", "| time_elapsed | 3321 |\n", "| total_timesteps | 614500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 123000 |\n", "| time_elapsed | 3324 |\n", "| total_timesteps | 615000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 123100 |\n", "| time_elapsed | 3327 |\n", "| total_timesteps | 615500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 123200 |\n", "| time_elapsed | 3329 |\n", "| total_timesteps | 616000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0449 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 123300 |\n", "| time_elapsed | 3332 |\n", "| total_timesteps | 616500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 123400 |\n", "| time_elapsed | 3335 |\n", "| total_timesteps | 617000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0391 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 123500 |\n", "| time_elapsed | 3337 |\n", "| total_timesteps | 617500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 123600 |\n", "| time_elapsed | 3340 |\n", "| total_timesteps | 618000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0508 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 123700 |\n", "| time_elapsed | 3343 |\n", "| total_timesteps | 618500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 123800 |\n", "| time_elapsed | 3345 |\n", "| total_timesteps | 619000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 123900 |\n", "| time_elapsed | 3348 |\n", "| total_timesteps | 619500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124000 |\n", "| time_elapsed | 3350 |\n", "| total_timesteps | 620000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.338 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124100 |\n", "| time_elapsed | 3353 |\n", "| total_timesteps | 620500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.853 |\n", "| value_loss | 1.26 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124200 |\n", "| time_elapsed | 3356 |\n", "| total_timesteps | 621000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0811 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124300 |\n", "| time_elapsed | 3358 |\n", "| total_timesteps | 621500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0701 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124400 |\n", "| time_elapsed | 3361 |\n", "| total_timesteps | 622000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124500 |\n", "| time_elapsed | 3364 |\n", "| total_timesteps | 622500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0458 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124600 |\n", "| time_elapsed | 3366 |\n", "| total_timesteps | 623000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0375 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124700 |\n", "| time_elapsed | 3369 |\n", "| total_timesteps | 623500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.225 |\n", "| value_loss | 0.343 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124800 |\n", "| time_elapsed | 3371 |\n", "| total_timesteps | 624000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0336 |\n", "| value_loss | 0.0027 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 124900 |\n", "| time_elapsed | 3374 |\n", "| total_timesteps | 624500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0406 |\n", "| value_loss | 0.00273 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125000 |\n", "| time_elapsed | 3377 |\n", "| total_timesteps | 625000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.0027 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125100 |\n", "| time_elapsed | 3379 |\n", "| total_timesteps | 625500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00257 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125200 |\n", "| time_elapsed | 3382 |\n", "| total_timesteps | 626000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.568 |\n", "| value_loss | 0.519 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125300 |\n", "| time_elapsed | 3384 |\n", "| total_timesteps | 626500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125400 |\n", "| time_elapsed | 3387 |\n", "| total_timesteps | 627000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125500 |\n", "| time_elapsed | 3390 |\n", "| total_timesteps | 627500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.332 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125600 |\n", "| time_elapsed | 3392 |\n", "| total_timesteps | 628000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.39 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125700 |\n", "| time_elapsed | 3395 |\n", "| total_timesteps | 628500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.959 |\n", "| value_loss | 0.899 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125800 |\n", "| time_elapsed | 3397 |\n", "| total_timesteps | 629000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 125900 |\n", "| time_elapsed | 3400 |\n", "| total_timesteps | 629500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0827 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126000 |\n", "| time_elapsed | 3403 |\n", "| total_timesteps | 630000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.35 |\n", "| value_loss | 0.699 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126100 |\n", "| time_elapsed | 3405 |\n", "| total_timesteps | 630500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126200 |\n", "| time_elapsed | 3408 |\n", "| total_timesteps | 631000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126300 |\n", "| time_elapsed | 3410 |\n", "| total_timesteps | 631500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.257 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126400 |\n", "| time_elapsed | 3413 |\n", "| total_timesteps | 632000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126500 |\n", "| time_elapsed | 3416 |\n", "| total_timesteps | 632500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0352 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126600 |\n", "| time_elapsed | 3418 |\n", "| total_timesteps | 633000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126700 |\n", "| time_elapsed | 3421 |\n", "| total_timesteps | 633500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0731 |\n", "| value_loss | 0.00252 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126800 |\n", "| time_elapsed | 3424 |\n", "| total_timesteps | 634000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.062 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 126900 |\n", "| time_elapsed | 3426 |\n", "| total_timesteps | 634500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127000 |\n", "| time_elapsed | 3429 |\n", "| total_timesteps | 635000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0517 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127100 |\n", "| time_elapsed | 3431 |\n", "| total_timesteps | 635500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0755 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127200 |\n", "| time_elapsed | 3434 |\n", "| total_timesteps | 636000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127300 |\n", "| time_elapsed | 3437 |\n", "| total_timesteps | 636500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127400 |\n", "| time_elapsed | 3439 |\n", "| total_timesteps | 637000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00244 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127500 |\n", "| time_elapsed | 3442 |\n", "| total_timesteps | 637500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127600 |\n", "| time_elapsed | 3444 |\n", "| total_timesteps | 638000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127700 |\n", "| time_elapsed | 3447 |\n", "| total_timesteps | 638500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.975 |\n", "| value_loss | 0.881 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127800 |\n", "| time_elapsed | 3450 |\n", "| total_timesteps | 639000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0773 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 127900 |\n", "| time_elapsed | 3452 |\n", "| total_timesteps | 639500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128000 |\n", "| time_elapsed | 3455 |\n", "| total_timesteps | 640000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128100 |\n", "| time_elapsed | 3457 |\n", "| total_timesteps | 640500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128200 |\n", "| time_elapsed | 3460 |\n", "| total_timesteps | 641000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0408 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128300 |\n", "| time_elapsed | 3463 |\n", "| total_timesteps | 641500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128400 |\n", "| time_elapsed | 3465 |\n", "| total_timesteps | 642000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128500 |\n", "| time_elapsed | 3468 |\n", "| total_timesteps | 642500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128600 |\n", "| time_elapsed | 3470 |\n", "| total_timesteps | 643000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0464 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128700 |\n", "| time_elapsed | 3473 |\n", "| total_timesteps | 643500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128800 |\n", "| time_elapsed | 3476 |\n", "| total_timesteps | 644000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.43 |\n", "| value_loss | 1.82 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 128900 |\n", "| time_elapsed | 3478 |\n", "| total_timesteps | 644500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00226 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129000 |\n", "| time_elapsed | 3481 |\n", "| total_timesteps | 645000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.059 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129100 |\n", "| time_elapsed | 3484 |\n", "| total_timesteps | 645500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0678 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129200 |\n", "| time_elapsed | 3486 |\n", "| total_timesteps | 646000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129300 |\n", "| time_elapsed | 3489 |\n", "| total_timesteps | 646500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129400 |\n", "| time_elapsed | 3492 |\n", "| total_timesteps | 647000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129500 |\n", "| time_elapsed | 3494 |\n", "| total_timesteps | 647500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129600 |\n", "| time_elapsed | 3497 |\n", "| total_timesteps | 648000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129700 |\n", "| time_elapsed | 3499 |\n", "| total_timesteps | 648500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129800 |\n", "| time_elapsed | 3502 |\n", "| total_timesteps | 649000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 129900 |\n", "| time_elapsed | 3505 |\n", "| total_timesteps | 649500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130000 |\n", "| time_elapsed | 3507 |\n", "| total_timesteps | 650000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130100 |\n", "| time_elapsed | 3510 |\n", "| total_timesteps | 650500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130200 |\n", "| time_elapsed | 3512 |\n", "| total_timesteps | 651000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0589 |\n", "| value_loss | 0.00232 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130300 |\n", "| time_elapsed | 3515 |\n", "| total_timesteps | 651500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130400 |\n", "| time_elapsed | 3517 |\n", "| total_timesteps | 652000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130500 |\n", "| time_elapsed | 3520 |\n", "| total_timesteps | 652500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0672 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130600 |\n", "| time_elapsed | 3523 |\n", "| total_timesteps | 653000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0725 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130700 |\n", "| time_elapsed | 3525 |\n", "| total_timesteps | 653500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130800 |\n", "| time_elapsed | 3528 |\n", "| total_timesteps | 654000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 130900 |\n", "| time_elapsed | 3530 |\n", "| total_timesteps | 654500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0671 |\n", "| value_loss | 0.0026 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131000 |\n", "| time_elapsed | 3533 |\n", "| total_timesteps | 655000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0623 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131100 |\n", "| time_elapsed | 3536 |\n", "| total_timesteps | 655500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0638 |\n", "| value_loss | 0.00235 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131200 |\n", "| time_elapsed | 3538 |\n", "| total_timesteps | 656000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.073 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131300 |\n", "| time_elapsed | 3541 |\n", "| total_timesteps | 656500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.01 |\n", "| value_loss | 0.877 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131400 |\n", "| time_elapsed | 3543 |\n", "| total_timesteps | 657000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0686 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131500 |\n", "| time_elapsed | 3546 |\n", "| total_timesteps | 657500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131600 |\n", "| time_elapsed | 3548 |\n", "| total_timesteps | 658000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.78 |\n", "| value_loss | 2.95 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131700 |\n", "| time_elapsed | 3551 |\n", "| total_timesteps | 658500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131800 |\n", "| time_elapsed | 3553 |\n", "| total_timesteps | 659000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.829 |\n", "| value_loss | 0.518 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 131900 |\n", "| time_elapsed | 3556 |\n", "| total_timesteps | 659500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0624 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132000 |\n", "| time_elapsed | 3559 |\n", "| total_timesteps | 660000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0654 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132100 |\n", "| time_elapsed | 3561 |\n", "| total_timesteps | 660500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0722 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132200 |\n", "| time_elapsed | 3564 |\n", "| total_timesteps | 661000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132300 |\n", "| time_elapsed | 3567 |\n", "| total_timesteps | 661500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0618 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132400 |\n", "| time_elapsed | 3569 |\n", "| total_timesteps | 662000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.54 |\n", "| value_loss | 2.54 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132500 |\n", "| time_elapsed | 3572 |\n", "| total_timesteps | 662500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0343 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132600 |\n", "| time_elapsed | 3574 |\n", "| total_timesteps | 663000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0628 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132700 |\n", "| time_elapsed | 3577 |\n", "| total_timesteps | 663500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0607 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132800 |\n", "| time_elapsed | 3580 |\n", "| total_timesteps | 664000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0647 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 132900 |\n", "| time_elapsed | 3582 |\n", "| total_timesteps | 664500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133000 |\n", "| time_elapsed | 3585 |\n", "| total_timesteps | 665000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133100 |\n", "| time_elapsed | 3588 |\n", "| total_timesteps | 665500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0581 |\n", "| value_loss | 0.00216 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133200 |\n", "| time_elapsed | 3590 |\n", "| total_timesteps | 666000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133300 |\n", "| time_elapsed | 3593 |\n", "| total_timesteps | 666500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.254 |\n", "| value_loss | 0.349 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133400 |\n", "| time_elapsed | 3596 |\n", "| total_timesteps | 667000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.043 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133500 |\n", "| time_elapsed | 3598 |\n", "| total_timesteps | 667500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133600 |\n", "| time_elapsed | 3601 |\n", "| total_timesteps | 668000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.482 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133700 |\n", "| time_elapsed | 3603 |\n", "| total_timesteps | 668500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00204 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133800 |\n", "| time_elapsed | 3606 |\n", "| total_timesteps | 669000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00198 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 133900 |\n", "| time_elapsed | 3608 |\n", "| total_timesteps | 669500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0477 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134000 |\n", "| time_elapsed | 3611 |\n", "| total_timesteps | 670000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.02 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134100 |\n", "| time_elapsed | 3614 |\n", "| total_timesteps | 670500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0512 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134200 |\n", "| time_elapsed | 3616 |\n", "| total_timesteps | 671000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.033 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134300 |\n", "| time_elapsed | 3619 |\n", "| total_timesteps | 671500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134400 |\n", "| time_elapsed | 3621 |\n", "| total_timesteps | 672000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.754 |\n", "| value_loss | 0.704 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134500 |\n", "| time_elapsed | 3624 |\n", "| total_timesteps | 672500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134600 |\n", "| time_elapsed | 3627 |\n", "| total_timesteps | 673000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0743 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134700 |\n", "| time_elapsed | 3629 |\n", "| total_timesteps | 673500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.19 |\n", "| value_loss | 1.09 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134800 |\n", "| time_elapsed | 3632 |\n", "| total_timesteps | 674000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0468 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 134900 |\n", "| time_elapsed | 3635 |\n", "| total_timesteps | 674500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.18 |\n", "| value_loss | 1.19 |\n", "------------------------------------\n", "Eval num_timesteps=675000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 675000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135000 |\n", "| time_elapsed | 3648 |\n", "| total_timesteps | 675000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135100 |\n", "| time_elapsed | 3651 |\n", "| total_timesteps | 675500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0578 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135200 |\n", "| time_elapsed | 3654 |\n", "| total_timesteps | 676000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00245 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135300 |\n", "| time_elapsed | 3656 |\n", "| total_timesteps | 676500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135400 |\n", "| time_elapsed | 3659 |\n", "| total_timesteps | 677000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135500 |\n", "| time_elapsed | 3662 |\n", "| total_timesteps | 677500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00236 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135600 |\n", "| time_elapsed | 3665 |\n", "| total_timesteps | 678000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135700 |\n", "| time_elapsed | 3667 |\n", "| total_timesteps | 678500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135800 |\n", "| time_elapsed | 3670 |\n", "| total_timesteps | 679000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 135900 |\n", "| time_elapsed | 3673 |\n", "| total_timesteps | 679500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136000 |\n", "| time_elapsed | 3676 |\n", "| total_timesteps | 680000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136100 |\n", "| time_elapsed | 3678 |\n", "| total_timesteps | 680500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0262 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136200 |\n", "| time_elapsed | 3681 |\n", "| total_timesteps | 681000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136300 |\n", "| time_elapsed | 3684 |\n", "| total_timesteps | 681500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0665 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136400 |\n", "| time_elapsed | 3687 |\n", "| total_timesteps | 682000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136500 |\n", "| time_elapsed | 3689 |\n", "| total_timesteps | 682500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0271 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136600 |\n", "| time_elapsed | 3692 |\n", "| total_timesteps | 683000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0565 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136700 |\n", "| time_elapsed | 3695 |\n", "| total_timesteps | 683500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136800 |\n", "| time_elapsed | 3698 |\n", "| total_timesteps | 684000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0357 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 136900 |\n", "| time_elapsed | 3700 |\n", "| total_timesteps | 684500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137000 |\n", "| time_elapsed | 3703 |\n", "| total_timesteps | 685000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.225 |\n", "| value_loss | 0.351 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137100 |\n", "| time_elapsed | 3706 |\n", "| total_timesteps | 685500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137200 |\n", "| time_elapsed | 3708 |\n", "| total_timesteps | 686000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0688 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137300 |\n", "| time_elapsed | 3711 |\n", "| total_timesteps | 686500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137400 |\n", "| time_elapsed | 3714 |\n", "| total_timesteps | 687000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137500 |\n", "| time_elapsed | 3717 |\n", "| total_timesteps | 687500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0242 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137600 |\n", "| time_elapsed | 3719 |\n", "| total_timesteps | 688000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137700 |\n", "| time_elapsed | 3722 |\n", "| total_timesteps | 688500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0312 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137800 |\n", "| time_elapsed | 3724 |\n", "| total_timesteps | 689000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0464 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 137900 |\n", "| time_elapsed | 3727 |\n", "| total_timesteps | 689500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138000 |\n", "| time_elapsed | 3730 |\n", "| total_timesteps | 690000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138100 |\n", "| time_elapsed | 3732 |\n", "| total_timesteps | 690500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138200 |\n", "| time_elapsed | 3735 |\n", "| total_timesteps | 691000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0264 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138300 |\n", "| time_elapsed | 3737 |\n", "| total_timesteps | 691500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138400 |\n", "| time_elapsed | 3740 |\n", "| total_timesteps | 692000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 138500 |\n", "| time_elapsed | 3743 |\n", "| total_timesteps | 692500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0255 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 138600 |\n", "| time_elapsed | 3745 |\n", "| total_timesteps | 693000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.62 |\n", "| value_loss | 2.55 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 138700 |\n", "| time_elapsed | 3748 |\n", "| total_timesteps | 693500 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 138800 |\n", "| time_elapsed | 3751 |\n", "| total_timesteps | 694000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 138900 |\n", "| time_elapsed | 3753 |\n", "| total_timesteps | 694500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139000 |\n", "| time_elapsed | 3756 |\n", "| total_timesteps | 695000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139100 |\n", "| time_elapsed | 3759 |\n", "| total_timesteps | 695500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0272 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139200 |\n", "| time_elapsed | 3761 |\n", "| total_timesteps | 696000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139300 |\n", "| time_elapsed | 3764 |\n", "| total_timesteps | 696500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.411 |\n", "| value_loss | 0.703 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139400 |\n", "| time_elapsed | 3766 |\n", "| total_timesteps | 697000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139500 |\n", "| time_elapsed | 3769 |\n", "| total_timesteps | 697500 |\n", "| train/ | |\n", "| entropy_loss | -1.09 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139600 |\n", "| time_elapsed | 3772 |\n", "| total_timesteps | 698000 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0801 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139700 |\n", "| time_elapsed | 3774 |\n", "| total_timesteps | 698500 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00249 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139800 |\n", "| time_elapsed | 3777 |\n", "| total_timesteps | 699000 |\n", "| train/ | |\n", "| entropy_loss | -1.07 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 139900 |\n", "| time_elapsed | 3780 |\n", "| total_timesteps | 699500 |\n", "| train/ | |\n", "| entropy_loss | -1.08 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0593 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140000 |\n", "| time_elapsed | 3782 |\n", "| total_timesteps | 700000 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0618 |\n", "| value_loss | 0.00227 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140100 |\n", "| time_elapsed | 3785 |\n", "| total_timesteps | 700500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.256 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140200 |\n", "| time_elapsed | 3787 |\n", "| total_timesteps | 701000 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140300 |\n", "| time_elapsed | 3790 |\n", "| total_timesteps | 701500 |\n", "| train/ | |\n", "| entropy_loss | -1.1 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0612 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140400 |\n", "| time_elapsed | 3793 |\n", "| total_timesteps | 702000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140500 |\n", "| time_elapsed | 3795 |\n", "| total_timesteps | 702500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.071 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140600 |\n", "| time_elapsed | 3798 |\n", "| total_timesteps | 703000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0742 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140700 |\n", "| time_elapsed | 3800 |\n", "| total_timesteps | 703500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0341 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140800 |\n", "| time_elapsed | 3803 |\n", "| total_timesteps | 704000 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0375 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 140900 |\n", "| time_elapsed | 3806 |\n", "| total_timesteps | 704500 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0353 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141000 |\n", "| time_elapsed | 3808 |\n", "| total_timesteps | 705000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.05 |\n", "| value_loss | 0.701 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141100 |\n", "| time_elapsed | 3811 |\n", "| total_timesteps | 705500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0289 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141200 |\n", "| time_elapsed | 3814 |\n", "| total_timesteps | 706000 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.789 |\n", "| value_loss | 0.701 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141300 |\n", "| time_elapsed | 3816 |\n", "| total_timesteps | 706500 |\n", "| train/ | |\n", "| entropy_loss | -1.12 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0227 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141400 |\n", "| time_elapsed | 3819 |\n", "| total_timesteps | 707000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141500 |\n", "| time_elapsed | 3821 |\n", "| total_timesteps | 707500 |\n", "| train/ | |\n", "| entropy_loss | -1.11 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0264 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141600 |\n", "| time_elapsed | 3824 |\n", "| total_timesteps | 708000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0558 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141700 |\n", "| time_elapsed | 3827 |\n", "| total_timesteps | 708500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141800 |\n", "| time_elapsed | 3829 |\n", "| total_timesteps | 709000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.323 |\n", "| value_loss | 0.175 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 141900 |\n", "| time_elapsed | 3832 |\n", "| total_timesteps | 709500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0243 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142000 |\n", "| time_elapsed | 3835 |\n", "| total_timesteps | 710000 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142100 |\n", "| time_elapsed | 3837 |\n", "| total_timesteps | 710500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0352 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142200 |\n", "| time_elapsed | 3840 |\n", "| total_timesteps | 711000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0612 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142300 |\n", "| time_elapsed | 3842 |\n", "| total_timesteps | 711500 |\n", "| train/ | |\n", "| entropy_loss | -1.14 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0359 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142400 |\n", "| time_elapsed | 3845 |\n", "| total_timesteps | 712000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142500 |\n", "| time_elapsed | 3848 |\n", "| total_timesteps | 712500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142600 |\n", "| time_elapsed | 3850 |\n", "| total_timesteps | 713000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0338 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142700 |\n", "| time_elapsed | 3853 |\n", "| total_timesteps | 713500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0547 |\n", "| value_loss | 0.00186 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142800 |\n", "| time_elapsed | 3855 |\n", "| total_timesteps | 714000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 142900 |\n", "| time_elapsed | 3858 |\n", "| total_timesteps | 714500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143000 |\n", "| time_elapsed | 3861 |\n", "| total_timesteps | 715000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143100 |\n", "| time_elapsed | 3863 |\n", "| total_timesteps | 715500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143200 |\n", "| time_elapsed | 3866 |\n", "| total_timesteps | 716000 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.332 |\n", "| value_loss | 0.526 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143300 |\n", "| time_elapsed | 3869 |\n", "| total_timesteps | 716500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0312 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143400 |\n", "| time_elapsed | 3871 |\n", "| total_timesteps | 717000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143500 |\n", "| time_elapsed | 3874 |\n", "| total_timesteps | 717500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143600 |\n", "| time_elapsed | 3876 |\n", "| total_timesteps | 718000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0682 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143700 |\n", "| time_elapsed | 3879 |\n", "| total_timesteps | 718500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143800 |\n", "| time_elapsed | 3882 |\n", "| total_timesteps | 719000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 143900 |\n", "| time_elapsed | 3884 |\n", "| total_timesteps | 719500 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.316 |\n", "| value_loss | 0.521 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144000 |\n", "| time_elapsed | 3887 |\n", "| total_timesteps | 720000 |\n", "| train/ | |\n", "| entropy_loss | -1.13 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144100 |\n", "| time_elapsed | 3889 |\n", "| total_timesteps | 720500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144200 |\n", "| time_elapsed | 3892 |\n", "| total_timesteps | 721000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0344 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144300 |\n", "| time_elapsed | 3895 |\n", "| total_timesteps | 721500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0611 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144400 |\n", "| time_elapsed | 3897 |\n", "| total_timesteps | 722000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.86 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144500 |\n", "| time_elapsed | 3900 |\n", "| total_timesteps | 722500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0595 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144600 |\n", "| time_elapsed | 3902 |\n", "| total_timesteps | 723000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.7 |\n", "| value_loss | 1.45 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144700 |\n", "| time_elapsed | 3905 |\n", "| total_timesteps | 723500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.483 |\n", "| value_loss | 0.35 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144800 |\n", "| time_elapsed | 3908 |\n", "| total_timesteps | 724000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0464 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 144900 |\n", "| time_elapsed | 3910 |\n", "| total_timesteps | 724500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0303 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145000 |\n", "| time_elapsed | 3913 |\n", "| total_timesteps | 725000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0359 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145100 |\n", "| time_elapsed | 3915 |\n", "| total_timesteps | 725500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145200 |\n", "| time_elapsed | 3918 |\n", "| total_timesteps | 726000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0394 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145300 |\n", "| time_elapsed | 3921 |\n", "| total_timesteps | 726500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0299 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145400 |\n", "| time_elapsed | 3923 |\n", "| total_timesteps | 727000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0358 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145500 |\n", "| time_elapsed | 3926 |\n", "| total_timesteps | 727500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00201 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145600 |\n", "| time_elapsed | 3929 |\n", "| total_timesteps | 728000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00203 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145700 |\n", "| time_elapsed | 3931 |\n", "| total_timesteps | 728500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0453 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145800 |\n", "| time_elapsed | 3934 |\n", "| total_timesteps | 729000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0513 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 145900 |\n", "| time_elapsed | 3936 |\n", "| total_timesteps | 729500 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.718 |\n", "| value_loss | 0.704 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146000 |\n", "| time_elapsed | 3939 |\n", "| total_timesteps | 730000 |\n", "| train/ | |\n", "| entropy_loss | -1.16 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146100 |\n", "| time_elapsed | 3942 |\n", "| total_timesteps | 730500 |\n", "| train/ | |\n", "| entropy_loss | -1.15 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0693 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146200 |\n", "| time_elapsed | 3944 |\n", "| total_timesteps | 731000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.891 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146300 |\n", "| time_elapsed | 3947 |\n", "| total_timesteps | 731500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0736 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146400 |\n", "| time_elapsed | 3949 |\n", "| total_timesteps | 732000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146500 |\n", "| time_elapsed | 3952 |\n", "| total_timesteps | 732500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0319 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146600 |\n", "| time_elapsed | 3955 |\n", "| total_timesteps | 733000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146700 |\n", "| time_elapsed | 3957 |\n", "| total_timesteps | 733500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146800 |\n", "| time_elapsed | 3960 |\n", "| total_timesteps | 734000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0528 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 146900 |\n", "| time_elapsed | 3963 |\n", "| total_timesteps | 734500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147000 |\n", "| time_elapsed | 3965 |\n", "| total_timesteps | 735000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147100 |\n", "| time_elapsed | 3968 |\n", "| total_timesteps | 735500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0326 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147200 |\n", "| time_elapsed | 3971 |\n", "| total_timesteps | 736000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.27 |\n", "| value_loss | 2.96 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147300 |\n", "| time_elapsed | 3973 |\n", "| total_timesteps | 736500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147400 |\n", "| time_elapsed | 3976 |\n", "| total_timesteps | 737000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0366 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147500 |\n", "| time_elapsed | 3979 |\n", "| total_timesteps | 737500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.879 |\n", "| value_loss | 0.885 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147600 |\n", "| time_elapsed | 3981 |\n", "| total_timesteps | 738000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.39 |\n", "| value_loss | 2.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147700 |\n", "| time_elapsed | 3984 |\n", "| total_timesteps | 738500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.866 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147800 |\n", "| time_elapsed | 3986 |\n", "| total_timesteps | 739000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.07 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 147900 |\n", "| time_elapsed | 3989 |\n", "| total_timesteps | 739500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0704 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148000 |\n", "| time_elapsed | 3992 |\n", "| total_timesteps | 740000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0395 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 519 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148100 |\n", "| time_elapsed | 3994 |\n", "| total_timesteps | 740500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0452 |\n", "| value_loss | 0.00197 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148200 |\n", "| time_elapsed | 3997 |\n", "| total_timesteps | 741000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148300 |\n", "| time_elapsed | 4000 |\n", "| total_timesteps | 741500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00165 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 520 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148400 |\n", "| time_elapsed | 4002 |\n", "| total_timesteps | 742000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148500 |\n", "| time_elapsed | 4005 |\n", "| total_timesteps | 742500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148600 |\n", "| time_elapsed | 4007 |\n", "| total_timesteps | 743000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0257 |\n", "| value_loss | 0.00198 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148700 |\n", "| time_elapsed | 4010 |\n", "| total_timesteps | 743500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148800 |\n", "| time_elapsed | 4012 |\n", "| total_timesteps | 744000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 148900 |\n", "| time_elapsed | 4015 |\n", "| total_timesteps | 744500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.61 |\n", "| value_loss | 0.887 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149000 |\n", "| time_elapsed | 4018 |\n", "| total_timesteps | 745000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0377 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149100 |\n", "| time_elapsed | 4020 |\n", "| total_timesteps | 745500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0368 |\n", "| value_loss | 0.00209 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149200 |\n", "| time_elapsed | 4023 |\n", "| total_timesteps | 746000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149300 |\n", "| time_elapsed | 4025 |\n", "| total_timesteps | 746500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0395 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149400 |\n", "| time_elapsed | 4028 |\n", "| total_timesteps | 747000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0692 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149500 |\n", "| time_elapsed | 4030 |\n", "| total_timesteps | 747500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149600 |\n", "| time_elapsed | 4033 |\n", "| total_timesteps | 748000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0835 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149700 |\n", "| time_elapsed | 4036 |\n", "| total_timesteps | 748500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.01 |\n", "| value_loss | 1.99 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149800 |\n", "| time_elapsed | 4038 |\n", "| total_timesteps | 749000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 149900 |\n", "| time_elapsed | 4041 |\n", "| total_timesteps | 749500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00224 |\n", "-------------------------------------\n", "Eval num_timesteps=750000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 750000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0638 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150000 |\n", "| time_elapsed | 4055 |\n", "| total_timesteps | 750000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150100 |\n", "| time_elapsed | 4060 |\n", "| total_timesteps | 750500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150200 |\n", "| time_elapsed | 4062 |\n", "| total_timesteps | 751000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150300 |\n", "| time_elapsed | 4065 |\n", "| total_timesteps | 751500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150400 |\n", "| time_elapsed | 4068 |\n", "| total_timesteps | 752000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.798 |\n", "| value_loss | 0.529 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150500 |\n", "| time_elapsed | 4070 |\n", "| total_timesteps | 752500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150600 |\n", "| time_elapsed | 4073 |\n", "| total_timesteps | 753000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0719 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150700 |\n", "| time_elapsed | 4075 |\n", "| total_timesteps | 753500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0383 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150800 |\n", "| time_elapsed | 4078 |\n", "| total_timesteps | 754000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0957 |\n", "| value_loss | 0.175 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 150900 |\n", "| time_elapsed | 4080 |\n", "| total_timesteps | 754500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0521 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151000 |\n", "| time_elapsed | 4083 |\n", "| total_timesteps | 755000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0452 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151100 |\n", "| time_elapsed | 4086 |\n", "| total_timesteps | 755500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151200 |\n", "| time_elapsed | 4088 |\n", "| total_timesteps | 756000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00205 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151300 |\n", "| time_elapsed | 4091 |\n", "| total_timesteps | 756500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.542 |\n", "| value_loss | 0.526 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151400 |\n", "| time_elapsed | 4094 |\n", "| total_timesteps | 757000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151500 |\n", "| time_elapsed | 4096 |\n", "| total_timesteps | 757500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.408 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151600 |\n", "| time_elapsed | 4099 |\n", "| total_timesteps | 758000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151700 |\n", "| time_elapsed | 4101 |\n", "| total_timesteps | 758500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151800 |\n", "| time_elapsed | 4104 |\n", "| total_timesteps | 759000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 151900 |\n", "| time_elapsed | 4106 |\n", "| total_timesteps | 759500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152000 |\n", "| time_elapsed | 4109 |\n", "| total_timesteps | 760000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152100 |\n", "| time_elapsed | 4112 |\n", "| total_timesteps | 760500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152200 |\n", "| time_elapsed | 4114 |\n", "| total_timesteps | 761000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152300 |\n", "| time_elapsed | 4117 |\n", "| total_timesteps | 761500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0644 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152400 |\n", "| time_elapsed | 4120 |\n", "| total_timesteps | 762000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00193 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152500 |\n", "| time_elapsed | 4122 |\n", "| total_timesteps | 762500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152600 |\n", "| time_elapsed | 4125 |\n", "| total_timesteps | 763000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152700 |\n", "| time_elapsed | 4127 |\n", "| total_timesteps | 763500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.636 |\n", "| value_loss | 0.524 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152800 |\n", "| time_elapsed | 4130 |\n", "| total_timesteps | 764000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 152900 |\n", "| time_elapsed | 4132 |\n", "| total_timesteps | 764500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.904 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 153000 |\n", "| time_elapsed | 4135 |\n", "| total_timesteps | 765000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 153100 |\n", "| time_elapsed | 4138 |\n", "| total_timesteps | 765500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0663 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 153200 |\n", "| time_elapsed | 4140 |\n", "| total_timesteps | 766000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 153300 |\n", "| time_elapsed | 4143 |\n", "| total_timesteps | 766500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0304 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153400 |\n", "| time_elapsed | 4145 |\n", "| total_timesteps | 767000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0477 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153500 |\n", "| time_elapsed | 4148 |\n", "| total_timesteps | 767500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.122 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153600 |\n", "| time_elapsed | 4151 |\n", "| total_timesteps | 768000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0435 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153700 |\n", "| time_elapsed | 4153 |\n", "| total_timesteps | 768500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0702 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153800 |\n", "| time_elapsed | 4156 |\n", "| total_timesteps | 769000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0336 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 153900 |\n", "| time_elapsed | 4158 |\n", "| total_timesteps | 769500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154000 |\n", "| time_elapsed | 4161 |\n", "| total_timesteps | 770000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0666 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154100 |\n", "| time_elapsed | 4164 |\n", "| total_timesteps | 770500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0287 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154200 |\n", "| time_elapsed | 4166 |\n", "| total_timesteps | 771000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.002 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154300 |\n", "| time_elapsed | 4169 |\n", "| total_timesteps | 771500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0291 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154400 |\n", "| time_elapsed | 4171 |\n", "| total_timesteps | 772000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154500 |\n", "| time_elapsed | 4174 |\n", "| total_timesteps | 772500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154600 |\n", "| time_elapsed | 4177 |\n", "| total_timesteps | 773000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0651 |\n", "| value_loss | 0.002 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154700 |\n", "| time_elapsed | 4179 |\n", "| total_timesteps | 773500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154800 |\n", "| time_elapsed | 4182 |\n", "| total_timesteps | 774000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 154900 |\n", "| time_elapsed | 4185 |\n", "| total_timesteps | 774500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.01 |\n", "| value_loss | 0.883 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155000 |\n", "| time_elapsed | 4187 |\n", "| total_timesteps | 775000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.941 |\n", "| value_loss | 1.66 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155100 |\n", "| time_elapsed | 4190 |\n", "| total_timesteps | 775500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0616 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155200 |\n", "| time_elapsed | 4192 |\n", "| total_timesteps | 776000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.205 |\n", "| value_loss | 0.176 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155300 |\n", "| time_elapsed | 4195 |\n", "| total_timesteps | 776500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.933 |\n", "| value_loss | 0.527 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155400 |\n", "| time_elapsed | 4198 |\n", "| total_timesteps | 777000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.613 |\n", "| value_loss | 0.528 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155500 |\n", "| time_elapsed | 4200 |\n", "| total_timesteps | 777500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155600 |\n", "| time_elapsed | 4203 |\n", "| total_timesteps | 778000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0574 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155700 |\n", "| time_elapsed | 4206 |\n", "| total_timesteps | 778500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.059 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155800 |\n", "| time_elapsed | 4208 |\n", "| total_timesteps | 779000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0647 |\n", "| value_loss | 0.00173 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 155900 |\n", "| time_elapsed | 4211 |\n", "| total_timesteps | 779500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0359 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156000 |\n", "| time_elapsed | 4213 |\n", "| total_timesteps | 780000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156100 |\n", "| time_elapsed | 4216 |\n", "| total_timesteps | 780500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0698 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156200 |\n", "| time_elapsed | 4218 |\n", "| total_timesteps | 781000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.153 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156300 |\n", "| time_elapsed | 4221 |\n", "| total_timesteps | 781500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00224 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156400 |\n", "| time_elapsed | 4224 |\n", "| total_timesteps | 782000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0587 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156500 |\n", "| time_elapsed | 4226 |\n", "| total_timesteps | 782500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156600 |\n", "| time_elapsed | 4229 |\n", "| total_timesteps | 783000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156700 |\n", "| time_elapsed | 4231 |\n", "| total_timesteps | 783500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0822 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156800 |\n", "| time_elapsed | 4234 |\n", "| total_timesteps | 784000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 156900 |\n", "| time_elapsed | 4237 |\n", "| total_timesteps | 784500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157000 |\n", "| time_elapsed | 4239 |\n", "| total_timesteps | 785000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157100 |\n", "| time_elapsed | 4242 |\n", "| total_timesteps | 785500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0363 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157200 |\n", "| time_elapsed | 4244 |\n", "| total_timesteps | 786000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157300 |\n", "| time_elapsed | 4247 |\n", "| total_timesteps | 786500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157400 |\n", "| time_elapsed | 4250 |\n", "| total_timesteps | 787000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0506 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157500 |\n", "| time_elapsed | 4252 |\n", "| total_timesteps | 787500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157600 |\n", "| time_elapsed | 4255 |\n", "| total_timesteps | 788000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0724 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157700 |\n", "| time_elapsed | 4257 |\n", "| total_timesteps | 788500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.09 |\n", "| value_loss | 2.39 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157800 |\n", "| time_elapsed | 4260 |\n", "| total_timesteps | 789000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.404 |\n", "| value_loss | 0.5 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 157900 |\n", "| time_elapsed | 4263 |\n", "| total_timesteps | 789500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.243 |\n", "| value_loss | 0.4 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158000 |\n", "| time_elapsed | 4265 |\n", "| total_timesteps | 790000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0374 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158100 |\n", "| time_elapsed | 4268 |\n", "| total_timesteps | 790500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158200 |\n", "| time_elapsed | 4270 |\n", "| total_timesteps | 791000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0513 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158300 |\n", "| time_elapsed | 4273 |\n", "| total_timesteps | 791500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158400 |\n", "| time_elapsed | 4276 |\n", "| total_timesteps | 792000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158500 |\n", "| time_elapsed | 4278 |\n", "| total_timesteps | 792500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158600 |\n", "| time_elapsed | 4281 |\n", "| total_timesteps | 793000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.049 |\n", "| value_loss | 0.00208 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158700 |\n", "| time_elapsed | 4283 |\n", "| total_timesteps | 793500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.58 |\n", "| value_loss | 0.879 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158800 |\n", "| time_elapsed | 4286 |\n", "| total_timesteps | 794000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.742 |\n", "| value_loss | 0.521 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 158900 |\n", "| time_elapsed | 4289 |\n", "| total_timesteps | 794500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.498 |\n", "| value_loss | 0.347 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159000 |\n", "| time_elapsed | 4291 |\n", "| total_timesteps | 795000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.05 |\n", "| value_loss | 0.522 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159100 |\n", "| time_elapsed | 4294 |\n", "| total_timesteps | 795500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0658 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159200 |\n", "| time_elapsed | 4296 |\n", "| total_timesteps | 796000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0554 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159300 |\n", "| time_elapsed | 4299 |\n", "| total_timesteps | 796500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159400 |\n", "| time_elapsed | 4302 |\n", "| total_timesteps | 797000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0769 |\n", "| value_loss | 0.00233 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159500 |\n", "| time_elapsed | 4304 |\n", "| total_timesteps | 797500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159600 |\n", "| time_elapsed | 4307 |\n", "| total_timesteps | 798000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159700 |\n", "| time_elapsed | 4309 |\n", "| total_timesteps | 798500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159800 |\n", "| time_elapsed | 4312 |\n", "| total_timesteps | 799000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0652 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 159900 |\n", "| time_elapsed | 4315 |\n", "| total_timesteps | 799500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160000 |\n", "| time_elapsed | 4317 |\n", "| total_timesteps | 800000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0616 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160100 |\n", "| time_elapsed | 4320 |\n", "| total_timesteps | 800500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.19 |\n", "| value_loss | 1.82 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160200 |\n", "| time_elapsed | 4323 |\n", "| total_timesteps | 801000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0396 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160300 |\n", "| time_elapsed | 4325 |\n", "| total_timesteps | 801500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0505 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160400 |\n", "| time_elapsed | 4328 |\n", "| total_timesteps | 802000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0348 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160500 |\n", "| time_elapsed | 4331 |\n", "| total_timesteps | 802500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00206 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 521 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160600 |\n", "| time_elapsed | 4333 |\n", "| total_timesteps | 803000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.114 |\n", "| value_loss | 0.174 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160700 |\n", "| time_elapsed | 4336 |\n", "| total_timesteps | 803500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160800 |\n", "| time_elapsed | 4338 |\n", "| total_timesteps | 804000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.251 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 160900 |\n", "| time_elapsed | 4341 |\n", "| total_timesteps | 804500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0598 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161000 |\n", "| time_elapsed | 4344 |\n", "| total_timesteps | 805000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0303 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161100 |\n", "| time_elapsed | 4346 |\n", "| total_timesteps | 805500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.08 |\n", "| value_loss | 0.881 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161200 |\n", "| time_elapsed | 4349 |\n", "| total_timesteps | 806000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.804 |\n", "| value_loss | 0.521 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161300 |\n", "| time_elapsed | 4351 |\n", "| total_timesteps | 806500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 522 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161400 |\n", "| time_elapsed | 4354 |\n", "| total_timesteps | 807000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161500 |\n", "| time_elapsed | 4357 |\n", "| total_timesteps | 807500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.056 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161600 |\n", "| time_elapsed | 4359 |\n", "| total_timesteps | 808000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0506 |\n", "| value_loss | 0.00218 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 523 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161700 |\n", "| time_elapsed | 4362 |\n", "| total_timesteps | 808500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161800 |\n", "| time_elapsed | 4365 |\n", "| total_timesteps | 809000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.639 |\n", "| value_loss | 0.701 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 161900 |\n", "| time_elapsed | 4367 |\n", "| total_timesteps | 809500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.034 |\n", "| value_loss | 0.00221 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162000 |\n", "| time_elapsed | 4370 |\n", "| total_timesteps | 810000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0348 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162100 |\n", "| time_elapsed | 4372 |\n", "| total_timesteps | 810500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0861 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162200 |\n", "| time_elapsed | 4375 |\n", "| total_timesteps | 811000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0532 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162300 |\n", "| time_elapsed | 4378 |\n", "| total_timesteps | 811500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0526 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162400 |\n", "| time_elapsed | 4380 |\n", "| total_timesteps | 812000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0549 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162500 |\n", "| time_elapsed | 4383 |\n", "| total_timesteps | 812500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0519 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162600 |\n", "| time_elapsed | 4385 |\n", "| total_timesteps | 813000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0818 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162700 |\n", "| time_elapsed | 4388 |\n", "| total_timesteps | 813500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162800 |\n", "| time_elapsed | 4391 |\n", "| total_timesteps | 814000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 162900 |\n", "| time_elapsed | 4393 |\n", "| total_timesteps | 814500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.27 |\n", "| value_loss | 1.26 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163000 |\n", "| time_elapsed | 4396 |\n", "| total_timesteps | 815000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0676 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163100 |\n", "| time_elapsed | 4399 |\n", "| total_timesteps | 815500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163200 |\n", "| time_elapsed | 4401 |\n", "| total_timesteps | 816000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0675 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163300 |\n", "| time_elapsed | 4404 |\n", "| total_timesteps | 816500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0598 |\n", "| value_loss | 0.00167 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163400 |\n", "| time_elapsed | 4406 |\n", "| total_timesteps | 817000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.935 |\n", "| value_loss | 0.707 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163500 |\n", "| time_elapsed | 4409 |\n", "| total_timesteps | 817500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163600 |\n", "| time_elapsed | 4412 |\n", "| total_timesteps | 818000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0655 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163700 |\n", "| time_elapsed | 4414 |\n", "| total_timesteps | 818500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.09 |\n", "| value_loss | 0.889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163800 |\n", "| time_elapsed | 4417 |\n", "| total_timesteps | 819000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.971 |\n", "| value_loss | 0.89 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 163900 |\n", "| time_elapsed | 4420 |\n", "| total_timesteps | 819500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.93 |\n", "| value_loss | 1.1 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164000 |\n", "| time_elapsed | 4422 |\n", "| total_timesteps | 820000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0486 |\n", "| value_loss | 0.00165 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164100 |\n", "| time_elapsed | 4425 |\n", "| total_timesteps | 820500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164200 |\n", "| time_elapsed | 4427 |\n", "| total_timesteps | 821000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00158 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164300 |\n", "| time_elapsed | 4430 |\n", "| total_timesteps | 821500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.27 |\n", "| value_loss | 0.893 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164400 |\n", "| time_elapsed | 4433 |\n", "| total_timesteps | 822000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.17 |\n", "| value_loss | 0.711 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164500 |\n", "| time_elapsed | 4435 |\n", "| total_timesteps | 822500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164600 |\n", "| time_elapsed | 4438 |\n", "| total_timesteps | 823000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0333 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164700 |\n", "| time_elapsed | 4441 |\n", "| total_timesteps | 823500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00152 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164800 |\n", "| time_elapsed | 4443 |\n", "| total_timesteps | 824000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00144 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 164900 |\n", "| time_elapsed | 4446 |\n", "| total_timesteps | 824500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.00148 |\n", "------------------------------------\n", "Eval num_timesteps=825000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 825000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.00146 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165000 |\n", "| time_elapsed | 4459 |\n", "| total_timesteps | 825000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165100 |\n", "| time_elapsed | 4462 |\n", "| total_timesteps | 825500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0416 |\n", "| value_loss | 0.00158 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165200 |\n", "| time_elapsed | 4465 |\n", "| total_timesteps | 826000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0528 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165300 |\n", "| time_elapsed | 4467 |\n", "| total_timesteps | 826500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0757 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165400 |\n", "| time_elapsed | 4470 |\n", "| total_timesteps | 827000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165500 |\n", "| time_elapsed | 4473 |\n", "| total_timesteps | 827500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165600 |\n", "| time_elapsed | 4475 |\n", "| total_timesteps | 828000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.295 |\n", "| value_loss | 0.352 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 184 |\n", "| iterations | 165700 |\n", "| time_elapsed | 4478 |\n", "| total_timesteps | 828500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 165800 |\n", "| time_elapsed | 4480 |\n", "| total_timesteps | 829000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.515 |\n", "| value_loss | 0.53 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 165900 |\n", "| time_elapsed | 4483 |\n", "| total_timesteps | 829500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0382 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166000 |\n", "| time_elapsed | 4486 |\n", "| total_timesteps | 830000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166100 |\n", "| time_elapsed | 4488 |\n", "| total_timesteps | 830500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166200 |\n", "| time_elapsed | 4491 |\n", "| total_timesteps | 831000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.06 |\n", "| value_loss | 2 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166300 |\n", "| time_elapsed | 4494 |\n", "| total_timesteps | 831500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166400 |\n", "| time_elapsed | 4496 |\n", "| total_timesteps | 832000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0518 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166500 |\n", "| time_elapsed | 4499 |\n", "| total_timesteps | 832500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0414 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166600 |\n", "| time_elapsed | 4501 |\n", "| total_timesteps | 833000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166700 |\n", "| time_elapsed | 4504 |\n", "| total_timesteps | 833500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00236 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166800 |\n", "| time_elapsed | 4507 |\n", "| total_timesteps | 834000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 166900 |\n", "| time_elapsed | 4509 |\n", "| total_timesteps | 834500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167000 |\n", "| time_elapsed | 4512 |\n", "| total_timesteps | 835000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0602 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167100 |\n", "| time_elapsed | 4514 |\n", "| total_timesteps | 835500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.502 |\n", "| value_loss | 0.526 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167200 |\n", "| time_elapsed | 4517 |\n", "| total_timesteps | 836000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167300 |\n", "| time_elapsed | 4520 |\n", "| total_timesteps | 836500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0319 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167400 |\n", "| time_elapsed | 4522 |\n", "| total_timesteps | 837000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167500 |\n", "| time_elapsed | 4525 |\n", "| total_timesteps | 837500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0329 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167600 |\n", "| time_elapsed | 4527 |\n", "| total_timesteps | 838000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167700 |\n", "| time_elapsed | 4530 |\n", "| total_timesteps | 838500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167800 |\n", "| time_elapsed | 4533 |\n", "| total_timesteps | 839000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0744 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 167900 |\n", "| time_elapsed | 4535 |\n", "| total_timesteps | 839500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168000 |\n", "| time_elapsed | 4538 |\n", "| total_timesteps | 840000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168100 |\n", "| time_elapsed | 4540 |\n", "| total_timesteps | 840500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168200 |\n", "| time_elapsed | 4543 |\n", "| total_timesteps | 841000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168300 |\n", "| time_elapsed | 4546 |\n", "| total_timesteps | 841500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0613 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168400 |\n", "| time_elapsed | 4549 |\n", "| total_timesteps | 842000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0477 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168500 |\n", "| time_elapsed | 4551 |\n", "| total_timesteps | 842500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0565 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168600 |\n", "| time_elapsed | 4554 |\n", "| total_timesteps | 843000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.6 |\n", "| value_loss | 0.885 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168700 |\n", "| time_elapsed | 4557 |\n", "| total_timesteps | 843500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168800 |\n", "| time_elapsed | 4560 |\n", "| total_timesteps | 844000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 168900 |\n", "| time_elapsed | 4563 |\n", "| total_timesteps | 844500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0561 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169000 |\n", "| time_elapsed | 4565 |\n", "| total_timesteps | 845000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169100 |\n", "| time_elapsed | 4568 |\n", "| total_timesteps | 845500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0543 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169200 |\n", "| time_elapsed | 4571 |\n", "| total_timesteps | 846000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169300 |\n", "| time_elapsed | 4574 |\n", "| total_timesteps | 846500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169400 |\n", "| time_elapsed | 4576 |\n", "| total_timesteps | 847000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.58 |\n", "| value_loss | 0.524 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169500 |\n", "| time_elapsed | 4579 |\n", "| total_timesteps | 847500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169600 |\n", "| time_elapsed | 4582 |\n", "| total_timesteps | 848000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0549 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169700 |\n", "| time_elapsed | 4584 |\n", "| total_timesteps | 848500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169800 |\n", "| time_elapsed | 4587 |\n", "| total_timesteps | 849000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0783 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 169900 |\n", "| time_elapsed | 4590 |\n", "| total_timesteps | 849500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170000 |\n", "| time_elapsed | 4592 |\n", "| total_timesteps | 850000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0657 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170100 |\n", "| time_elapsed | 4595 |\n", "| total_timesteps | 850500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0576 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170200 |\n", "| time_elapsed | 4597 |\n", "| total_timesteps | 851000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0855 |\n", "| value_loss | 0.00234 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170300 |\n", "| time_elapsed | 4600 |\n", "| total_timesteps | 851500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170400 |\n", "| time_elapsed | 4603 |\n", "| total_timesteps | 852000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.516 |\n", "| value_loss | 0.523 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170500 |\n", "| time_elapsed | 4605 |\n", "| total_timesteps | 852500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170600 |\n", "| time_elapsed | 4608 |\n", "| total_timesteps | 853000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0803 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170700 |\n", "| time_elapsed | 4610 |\n", "| total_timesteps | 853500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170800 |\n", "| time_elapsed | 4613 |\n", "| total_timesteps | 854000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 170900 |\n", "| time_elapsed | 4616 |\n", "| total_timesteps | 854500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0519 |\n", "| value_loss | 0.00209 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171000 |\n", "| time_elapsed | 4618 |\n", "| total_timesteps | 855000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171100 |\n", "| time_elapsed | 4621 |\n", "| total_timesteps | 855500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0568 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171200 |\n", "| time_elapsed | 4623 |\n", "| total_timesteps | 856000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.52 |\n", "| value_loss | 0.883 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171300 |\n", "| time_elapsed | 4626 |\n", "| total_timesteps | 856500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0517 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171400 |\n", "| time_elapsed | 4628 |\n", "| total_timesteps | 857000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0546 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171500 |\n", "| time_elapsed | 4631 |\n", "| total_timesteps | 857500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171600 |\n", "| time_elapsed | 4634 |\n", "| total_timesteps | 858000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0321 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171700 |\n", "| time_elapsed | 4636 |\n", "| total_timesteps | 858500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0541 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171800 |\n", "| time_elapsed | 4639 |\n", "| total_timesteps | 859000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 171900 |\n", "| time_elapsed | 4641 |\n", "| total_timesteps | 859500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.399 |\n", "| value_loss | 0.345 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172000 |\n", "| time_elapsed | 4644 |\n", "| total_timesteps | 860000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0598 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172100 |\n", "| time_elapsed | 4646 |\n", "| total_timesteps | 860500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172200 |\n", "| time_elapsed | 4649 |\n", "| total_timesteps | 861000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.02 |\n", "| value_loss | 0.702 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172300 |\n", "| time_elapsed | 4651 |\n", "| total_timesteps | 861500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172400 |\n", "| time_elapsed | 4654 |\n", "| total_timesteps | 862000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0339 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172500 |\n", "| time_elapsed | 4657 |\n", "| total_timesteps | 862500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172600 |\n", "| time_elapsed | 4659 |\n", "| total_timesteps | 863000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.161 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172700 |\n", "| time_elapsed | 4662 |\n", "| total_timesteps | 863500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.0024 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172800 |\n", "| time_elapsed | 4664 |\n", "| total_timesteps | 864000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0852 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 172900 |\n", "| time_elapsed | 4667 |\n", "| total_timesteps | 864500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.23 |\n", "| value_loss | 0.698 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173000 |\n", "| time_elapsed | 4669 |\n", "| total_timesteps | 865000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0515 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173100 |\n", "| time_elapsed | 4672 |\n", "| total_timesteps | 865500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173200 |\n", "| time_elapsed | 4675 |\n", "| total_timesteps | 866000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.063 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173300 |\n", "| time_elapsed | 4677 |\n", "| total_timesteps | 866500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173400 |\n", "| time_elapsed | 4680 |\n", "| total_timesteps | 867000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173500 |\n", "| time_elapsed | 4682 |\n", "| total_timesteps | 867500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0715 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173600 |\n", "| time_elapsed | 4685 |\n", "| total_timesteps | 868000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173700 |\n", "| time_elapsed | 4687 |\n", "| total_timesteps | 868500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173800 |\n", "| time_elapsed | 4690 |\n", "| total_timesteps | 869000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 173900 |\n", "| time_elapsed | 4693 |\n", "| total_timesteps | 869500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174000 |\n", "| time_elapsed | 4695 |\n", "| total_timesteps | 870000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.25 |\n", "| value_loss | 0.881 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174100 |\n", "| time_elapsed | 4698 |\n", "| total_timesteps | 870500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0704 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174200 |\n", "| time_elapsed | 4700 |\n", "| total_timesteps | 871000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174300 |\n", "| time_elapsed | 4703 |\n", "| total_timesteps | 871500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0357 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174400 |\n", "| time_elapsed | 4705 |\n", "| total_timesteps | 872000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0517 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174500 |\n", "| time_elapsed | 4708 |\n", "| total_timesteps | 872500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174600 |\n", "| time_elapsed | 4710 |\n", "| total_timesteps | 873000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174700 |\n", "| time_elapsed | 4713 |\n", "| total_timesteps | 873500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0382 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174800 |\n", "| time_elapsed | 4716 |\n", "| total_timesteps | 874000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.483 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 174900 |\n", "| time_elapsed | 4718 |\n", "| total_timesteps | 874500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0595 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175000 |\n", "| time_elapsed | 4721 |\n", "| total_timesteps | 875000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175100 |\n", "| time_elapsed | 4723 |\n", "| total_timesteps | 875500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175200 |\n", "| time_elapsed | 4726 |\n", "| total_timesteps | 876000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175300 |\n", "| time_elapsed | 4729 |\n", "| total_timesteps | 876500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0574 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175400 |\n", "| time_elapsed | 4731 |\n", "| total_timesteps | 877000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.0019 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175500 |\n", "| time_elapsed | 4734 |\n", "| total_timesteps | 877500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175600 |\n", "| time_elapsed | 4736 |\n", "| total_timesteps | 878000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175700 |\n", "| time_elapsed | 4739 |\n", "| total_timesteps | 878500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175800 |\n", "| time_elapsed | 4741 |\n", "| total_timesteps | 879000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0661 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 175900 |\n", "| time_elapsed | 4744 |\n", "| total_timesteps | 879500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176000 |\n", "| time_elapsed | 4746 |\n", "| total_timesteps | 880000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176100 |\n", "| time_elapsed | 4749 |\n", "| total_timesteps | 880500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.948 |\n", "| value_loss | 1.1 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176200 |\n", "| time_elapsed | 4752 |\n", "| total_timesteps | 881000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176300 |\n", "| time_elapsed | 4754 |\n", "| total_timesteps | 881500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176400 |\n", "| time_elapsed | 4757 |\n", "| total_timesteps | 882000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176500 |\n", "| time_elapsed | 4759 |\n", "| total_timesteps | 882500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0546 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176600 |\n", "| time_elapsed | 4762 |\n", "| total_timesteps | 883000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.992 |\n", "| value_loss | 0.707 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176700 |\n", "| time_elapsed | 4765 |\n", "| total_timesteps | 883500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176800 |\n", "| time_elapsed | 4767 |\n", "| total_timesteps | 884000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.533 |\n", "| value_loss | 0.351 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 176900 |\n", "| time_elapsed | 4770 |\n", "| total_timesteps | 884500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0345 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177000 |\n", "| time_elapsed | 4772 |\n", "| total_timesteps | 885000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177100 |\n", "| time_elapsed | 4775 |\n", "| total_timesteps | 885500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0367 |\n", "| value_loss | 0.00158 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177200 |\n", "| time_elapsed | 4777 |\n", "| total_timesteps | 886000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.00169 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177300 |\n", "| time_elapsed | 4780 |\n", "| total_timesteps | 886500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0412 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177400 |\n", "| time_elapsed | 4782 |\n", "| total_timesteps | 887000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177500 |\n", "| time_elapsed | 4785 |\n", "| total_timesteps | 887500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0439 |\n", "| value_loss | 0.00167 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177600 |\n", "| time_elapsed | 4788 |\n", "| total_timesteps | 888000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00166 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177700 |\n", "| time_elapsed | 4790 |\n", "| total_timesteps | 888500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00163 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177800 |\n", "| time_elapsed | 4793 |\n", "| total_timesteps | 889000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.02 |\n", "| value_loss | 0.893 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 177900 |\n", "| time_elapsed | 4795 |\n", "| total_timesteps | 889500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0662 |\n", "| value_loss | 0.0016 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178000 |\n", "| time_elapsed | 4798 |\n", "| total_timesteps | 890000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178100 |\n", "| time_elapsed | 4801 |\n", "| total_timesteps | 890500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178200 |\n", "| time_elapsed | 4803 |\n", "| total_timesteps | 891000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178300 |\n", "| time_elapsed | 4806 |\n", "| total_timesteps | 891500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.99 |\n", "| value_loss | 0.706 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178400 |\n", "| time_elapsed | 4808 |\n", "| total_timesteps | 892000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.069 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178500 |\n", "| time_elapsed | 4811 |\n", "| total_timesteps | 892500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0669 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178600 |\n", "| time_elapsed | 4813 |\n", "| total_timesteps | 893000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0487 |\n", "| value_loss | 0.00162 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178700 |\n", "| time_elapsed | 4816 |\n", "| total_timesteps | 893500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0366 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178800 |\n", "| time_elapsed | 4819 |\n", "| total_timesteps | 894000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 178900 |\n", "| time_elapsed | 4821 |\n", "| total_timesteps | 894500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0468 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179000 |\n", "| time_elapsed | 4824 |\n", "| total_timesteps | 895000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0528 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179100 |\n", "| time_elapsed | 4826 |\n", "| total_timesteps | 895500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0702 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179200 |\n", "| time_elapsed | 4829 |\n", "| total_timesteps | 896000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179300 |\n", "| time_elapsed | 4832 |\n", "| total_timesteps | 896500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179400 |\n", "| time_elapsed | 4834 |\n", "| total_timesteps | 897000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0486 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179500 |\n", "| time_elapsed | 4837 |\n", "| total_timesteps | 897500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.23 |\n", "| value_loss | 1.44 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179600 |\n", "| time_elapsed | 4839 |\n", "| total_timesteps | 898000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179700 |\n", "| time_elapsed | 4842 |\n", "| total_timesteps | 898500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.28 |\n", "| value_loss | 0.88 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179800 |\n", "| time_elapsed | 4844 |\n", "| total_timesteps | 899000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 179900 |\n", "| time_elapsed | 4847 |\n", "| total_timesteps | 899500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "Eval num_timesteps=900000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 900000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180000 |\n", "| time_elapsed | 4860 |\n", "| total_timesteps | 900000 |\n", "---------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180100 |\n", "| time_elapsed | 4863 |\n", "| total_timesteps | 900500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00205 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180200 |\n", "| time_elapsed | 4865 |\n", "| total_timesteps | 901000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0666 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180300 |\n", "| time_elapsed | 4868 |\n", "| total_timesteps | 901500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180400 |\n", "| time_elapsed | 4870 |\n", "| total_timesteps | 902000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0594 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180500 |\n", "| time_elapsed | 4873 |\n", "| total_timesteps | 902500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.538 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180600 |\n", "| time_elapsed | 4875 |\n", "| total_timesteps | 903000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0679 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180700 |\n", "| time_elapsed | 4878 |\n", "| total_timesteps | 903500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180800 |\n", "| time_elapsed | 4881 |\n", "| total_timesteps | 904000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.047 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 180900 |\n", "| time_elapsed | 4883 |\n", "| total_timesteps | 904500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181000 |\n", "| time_elapsed | 4886 |\n", "| total_timesteps | 905000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.268 |\n", "| value_loss | 0.327 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181100 |\n", "| time_elapsed | 4888 |\n", "| total_timesteps | 905500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181200 |\n", "| time_elapsed | 4891 |\n", "| total_timesteps | 906000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181300 |\n", "| time_elapsed | 4894 |\n", "| total_timesteps | 906500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0586 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181400 |\n", "| time_elapsed | 4896 |\n", "| total_timesteps | 907000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181500 |\n", "| time_elapsed | 4899 |\n", "| total_timesteps | 907500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0441 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181600 |\n", "| time_elapsed | 4901 |\n", "| total_timesteps | 908000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181700 |\n", "| time_elapsed | 4904 |\n", "| total_timesteps | 908500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181800 |\n", "| time_elapsed | 4907 |\n", "| total_timesteps | 909000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0539 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 181900 |\n", "| time_elapsed | 4909 |\n", "| total_timesteps | 909500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0468 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182000 |\n", "| time_elapsed | 4912 |\n", "| total_timesteps | 910000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182100 |\n", "| time_elapsed | 4915 |\n", "| total_timesteps | 910500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.87 |\n", "| value_loss | 0.528 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182200 |\n", "| time_elapsed | 4917 |\n", "| total_timesteps | 911000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182300 |\n", "| time_elapsed | 4920 |\n", "| total_timesteps | 911500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.598 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182400 |\n", "| time_elapsed | 4922 |\n", "| total_timesteps | 912000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182500 |\n", "| time_elapsed | 4925 |\n", "| total_timesteps | 912500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0645 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182600 |\n", "| time_elapsed | 4927 |\n", "| total_timesteps | 913000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.00183 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182700 |\n", "| time_elapsed | 4930 |\n", "| total_timesteps | 913500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00168 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182800 |\n", "| time_elapsed | 4932 |\n", "| total_timesteps | 914000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 182900 |\n", "| time_elapsed | 4935 |\n", "| total_timesteps | 914500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0374 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183000 |\n", "| time_elapsed | 4938 |\n", "| total_timesteps | 915000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.054 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183100 |\n", "| time_elapsed | 4940 |\n", "| total_timesteps | 915500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0532 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183200 |\n", "| time_elapsed | 4943 |\n", "| total_timesteps | 916000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183300 |\n", "| time_elapsed | 4945 |\n", "| total_timesteps | 916500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183400 |\n", "| time_elapsed | 4948 |\n", "| total_timesteps | 917000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.042 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183500 |\n", "| time_elapsed | 4951 |\n", "| total_timesteps | 917500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183600 |\n", "| time_elapsed | 4953 |\n", "| total_timesteps | 918000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.002 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183700 |\n", "| time_elapsed | 4956 |\n", "| total_timesteps | 918500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0715 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183800 |\n", "| time_elapsed | 4958 |\n", "| total_timesteps | 919000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0544 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 183900 |\n", "| time_elapsed | 4961 |\n", "| total_timesteps | 919500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.135 |\n", "| value_loss | 0.175 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184000 |\n", "| time_elapsed | 4963 |\n", "| total_timesteps | 920000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184100 |\n", "| time_elapsed | 4966 |\n", "| total_timesteps | 920500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184200 |\n", "| time_elapsed | 4969 |\n", "| total_timesteps | 921000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184300 |\n", "| time_elapsed | 4971 |\n", "| total_timesteps | 921500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0489 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184400 |\n", "| time_elapsed | 4974 |\n", "| total_timesteps | 922000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0439 |\n", "| value_loss | 0.00175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184500 |\n", "| time_elapsed | 4976 |\n", "| total_timesteps | 922500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0643 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184600 |\n", "| time_elapsed | 4979 |\n", "| total_timesteps | 923000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184700 |\n", "| time_elapsed | 4981 |\n", "| total_timesteps | 923500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.553 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184800 |\n", "| time_elapsed | 4984 |\n", "| total_timesteps | 924000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 184900 |\n", "| time_elapsed | 4986 |\n", "| total_timesteps | 924500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185000 |\n", "| time_elapsed | 4989 |\n", "| total_timesteps | 925000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185100 |\n", "| time_elapsed | 4992 |\n", "| total_timesteps | 925500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185200 |\n", "| time_elapsed | 4994 |\n", "| total_timesteps | 926000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.49 |\n", "| value_loss | 1.83 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185300 |\n", "| time_elapsed | 4997 |\n", "| total_timesteps | 926500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.07 |\n", "| value_loss | 0.0019 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185400 |\n", "| time_elapsed | 4999 |\n", "| total_timesteps | 927000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185500 |\n", "| time_elapsed | 5002 |\n", "| total_timesteps | 927500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185600 |\n", "| time_elapsed | 5004 |\n", "| total_timesteps | 928000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185700 |\n", "| time_elapsed | 5007 |\n", "| total_timesteps | 928500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0721 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185800 |\n", "| time_elapsed | 5009 |\n", "| total_timesteps | 929000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.3 |\n", "| value_loss | 1.83 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 185900 |\n", "| time_elapsed | 5012 |\n", "| total_timesteps | 929500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.29 |\n", "| value_loss | 0.881 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186000 |\n", "| time_elapsed | 5015 |\n", "| total_timesteps | 930000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.49 |\n", "| value_loss | 1.19 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186100 |\n", "| time_elapsed | 5017 |\n", "| total_timesteps | 930500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186200 |\n", "| time_elapsed | 5020 |\n", "| total_timesteps | 931000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186300 |\n", "| time_elapsed | 5022 |\n", "| total_timesteps | 931500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186400 |\n", "| time_elapsed | 5025 |\n", "| total_timesteps | 932000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0452 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186500 |\n", "| time_elapsed | 5028 |\n", "| total_timesteps | 932500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186600 |\n", "| time_elapsed | 5030 |\n", "| total_timesteps | 933000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186700 |\n", "| time_elapsed | 5033 |\n", "| total_timesteps | 933500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0398 |\n", "| value_loss | 0.00196 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186800 |\n", "| time_elapsed | 5035 |\n", "| total_timesteps | 934000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0548 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 186900 |\n", "| time_elapsed | 5038 |\n", "| total_timesteps | 934500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0658 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187000 |\n", "| time_elapsed | 5040 |\n", "| total_timesteps | 935000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187100 |\n", "| time_elapsed | 5043 |\n", "| total_timesteps | 935500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187200 |\n", "| time_elapsed | 5045 |\n", "| total_timesteps | 936000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.02 |\n", "| value_loss | 0.523 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187300 |\n", "| time_elapsed | 5048 |\n", "| total_timesteps | 936500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0669 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187400 |\n", "| time_elapsed | 5051 |\n", "| total_timesteps | 937000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187500 |\n", "| time_elapsed | 5053 |\n", "| total_timesteps | 937500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187600 |\n", "| time_elapsed | 5056 |\n", "| total_timesteps | 938000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.554 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187700 |\n", "| time_elapsed | 5059 |\n", "| total_timesteps | 938500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187800 |\n", "| time_elapsed | 5061 |\n", "| total_timesteps | 939000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 187900 |\n", "| time_elapsed | 5064 |\n", "| total_timesteps | 939500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188000 |\n", "| time_elapsed | 5066 |\n", "| total_timesteps | 940000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0346 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188100 |\n", "| time_elapsed | 5069 |\n", "| total_timesteps | 940500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188200 |\n", "| time_elapsed | 5071 |\n", "| total_timesteps | 941000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.082 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188300 |\n", "| time_elapsed | 5074 |\n", "| total_timesteps | 941500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.072 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188400 |\n", "| time_elapsed | 5077 |\n", "| total_timesteps | 942000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0805 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188500 |\n", "| time_elapsed | 5079 |\n", "| total_timesteps | 942500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.062 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188600 |\n", "| time_elapsed | 5082 |\n", "| total_timesteps | 943000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0576 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 550 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188700 |\n", "| time_elapsed | 5084 |\n", "| total_timesteps | 943500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.87 |\n", "| value_loss | 2.56 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 550 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188800 |\n", "| time_elapsed | 5087 |\n", "| total_timesteps | 944000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.065 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 188900 |\n", "| time_elapsed | 5089 |\n", "| total_timesteps | 944500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.69 |\n", "| value_loss | 1.44 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189000 |\n", "| time_elapsed | 5092 |\n", "| total_timesteps | 945000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | nan |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -2.05 |\n", "| value_loss | 1.94 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189100 |\n", "| time_elapsed | 5094 |\n", "| total_timesteps | 945500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.785 |\n", "| value_loss | 0.528 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189200 |\n", "| time_elapsed | 5097 |\n", "| total_timesteps | 946000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.765 |\n", "| value_loss | 0.705 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189300 |\n", "| time_elapsed | 5100 |\n", "| total_timesteps | 946500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0695 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189400 |\n", "| time_elapsed | 5102 |\n", "| total_timesteps | 947000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189500 |\n", "| time_elapsed | 5105 |\n", "| total_timesteps | 947500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189600 |\n", "| time_elapsed | 5107 |\n", "| total_timesteps | 948000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.047 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 550 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189700 |\n", "| time_elapsed | 5110 |\n", "| total_timesteps | 948500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189800 |\n", "| time_elapsed | 5112 |\n", "| total_timesteps | 949000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 189900 |\n", "| time_elapsed | 5115 |\n", "| total_timesteps | 949500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.1 |\n", "| value_loss | 0.889 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190000 |\n", "| time_elapsed | 5117 |\n", "| total_timesteps | 950000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.367 |\n", "| value_loss | 0.352 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190100 |\n", "| time_elapsed | 5120 |\n", "| total_timesteps | 950500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0677 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190200 |\n", "| time_elapsed | 5122 |\n", "| total_timesteps | 951000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0688 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190300 |\n", "| time_elapsed | 5125 |\n", "| total_timesteps | 951500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.307 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190400 |\n", "| time_elapsed | 5128 |\n", "| total_timesteps | 952000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190500 |\n", "| time_elapsed | 5130 |\n", "| total_timesteps | 952500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190600 |\n", "| time_elapsed | 5133 |\n", "| total_timesteps | 953000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.567 |\n", "| value_loss | 0.35 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190700 |\n", "| time_elapsed | 5135 |\n", "| total_timesteps | 953500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.926 |\n", "| value_loss | 0.703 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190800 |\n", "| time_elapsed | 5138 |\n", "| total_timesteps | 954000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.716 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 190900 |\n", "| time_elapsed | 5140 |\n", "| total_timesteps | 954500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.192 |\n", "| value_loss | 0.175 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191000 |\n", "| time_elapsed | 5143 |\n", "| total_timesteps | 955000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191100 |\n", "| time_elapsed | 5145 |\n", "| total_timesteps | 955500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191200 |\n", "| time_elapsed | 5148 |\n", "| total_timesteps | 956000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191300 |\n", "| time_elapsed | 5151 |\n", "| total_timesteps | 956500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191400 |\n", "| time_elapsed | 5153 |\n", "| total_timesteps | 957000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191500 |\n", "| time_elapsed | 5156 |\n", "| total_timesteps | 957500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0528 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191600 |\n", "| time_elapsed | 5158 |\n", "| total_timesteps | 958000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191700 |\n", "| time_elapsed | 5161 |\n", "| total_timesteps | 958500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.459 |\n", "| value_loss | 0.526 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 550 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191800 |\n", "| time_elapsed | 5164 |\n", "| total_timesteps | 959000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0544 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 550 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 191900 |\n", "| time_elapsed | 5166 |\n", "| total_timesteps | 959500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192000 |\n", "| time_elapsed | 5169 |\n", "| total_timesteps | 960000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.13 |\n", "| value_loss | 0.883 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192100 |\n", "| time_elapsed | 5171 |\n", "| total_timesteps | 960500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.037 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192200 |\n", "| time_elapsed | 5174 |\n", "| total_timesteps | 961000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0388 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192300 |\n", "| time_elapsed | 5176 |\n", "| total_timesteps | 961500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0568 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192400 |\n", "| time_elapsed | 5179 |\n", "| total_timesteps | 962000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192500 |\n", "| time_elapsed | 5182 |\n", "| total_timesteps | 962500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.0022 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192600 |\n", "| time_elapsed | 5184 |\n", "| total_timesteps | 963000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0489 |\n", "| value_loss | 0.00211 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192700 |\n", "| time_elapsed | 5187 |\n", "| total_timesteps | 963500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192800 |\n", "| time_elapsed | 5189 |\n", "| total_timesteps | 964000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0694 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 192900 |\n", "| time_elapsed | 5192 |\n", "| total_timesteps | 964500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0453 |\n", "| value_loss | 0.00235 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193000 |\n", "| time_elapsed | 5194 |\n", "| total_timesteps | 965000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193100 |\n", "| time_elapsed | 5197 |\n", "| total_timesteps | 965500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193200 |\n", "| time_elapsed | 5200 |\n", "| total_timesteps | 966000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0638 |\n", "| value_loss | 0.00202 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193300 |\n", "| time_elapsed | 5202 |\n", "| total_timesteps | 966500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0637 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193400 |\n", "| time_elapsed | 5205 |\n", "| total_timesteps | 967000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.524 |\n", "| value_loss | 0.526 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193500 |\n", "| time_elapsed | 5207 |\n", "| total_timesteps | 967500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0589 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193600 |\n", "| time_elapsed | 5210 |\n", "| total_timesteps | 968000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193700 |\n", "| time_elapsed | 5212 |\n", "| total_timesteps | 968500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0616 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193800 |\n", "| time_elapsed | 5215 |\n", "| total_timesteps | 969000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 193900 |\n", "| time_elapsed | 5218 |\n", "| total_timesteps | 969500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194000 |\n", "| time_elapsed | 5220 |\n", "| total_timesteps | 970000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194100 |\n", "| time_elapsed | 5223 |\n", "| total_timesteps | 970500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0574 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194200 |\n", "| time_elapsed | 5225 |\n", "| total_timesteps | 971000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0445 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194300 |\n", "| time_elapsed | 5228 |\n", "| total_timesteps | 971500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194400 |\n", "| time_elapsed | 5230 |\n", "| total_timesteps | 972000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0735 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194500 |\n", "| time_elapsed | 5233 |\n", "| total_timesteps | 972500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0894 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194600 |\n", "| time_elapsed | 5235 |\n", "| total_timesteps | 973000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00227 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194700 |\n", "| time_elapsed | 5238 |\n", "| total_timesteps | 973500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0565 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194800 |\n", "| time_elapsed | 5241 |\n", "| total_timesteps | 974000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.047 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 194900 |\n", "| time_elapsed | 5243 |\n", "| total_timesteps | 974500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "Eval num_timesteps=975000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 975000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.259 |\n", "| value_loss | 0.371 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195000 |\n", "| time_elapsed | 5256 |\n", "| total_timesteps | 975000 |\n", "---------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195100 |\n", "| time_elapsed | 5259 |\n", "| total_timesteps | 975500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00205 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195200 |\n", "| time_elapsed | 5261 |\n", "| total_timesteps | 976000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195300 |\n", "| time_elapsed | 5264 |\n", "| total_timesteps | 976500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0678 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195400 |\n", "| time_elapsed | 5267 |\n", "| total_timesteps | 977000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.292 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195500 |\n", "| time_elapsed | 5269 |\n", "| total_timesteps | 977500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195600 |\n", "| time_elapsed | 5272 |\n", "| total_timesteps | 978000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00189 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195700 |\n", "| time_elapsed | 5274 |\n", "| total_timesteps | 978500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195800 |\n", "| time_elapsed | 5277 |\n", "| total_timesteps | 979000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 195900 |\n", "| time_elapsed | 5280 |\n", "| total_timesteps | 979500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.0021 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196000 |\n", "| time_elapsed | 5282 |\n", "| total_timesteps | 980000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0374 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196100 |\n", "| time_elapsed | 5285 |\n", "| total_timesteps | 980500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196200 |\n", "| time_elapsed | 5287 |\n", "| total_timesteps | 981000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196300 |\n", "| time_elapsed | 5290 |\n", "| total_timesteps | 981500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0526 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196400 |\n", "| time_elapsed | 5292 |\n", "| total_timesteps | 982000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00181 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196500 |\n", "| time_elapsed | 5295 |\n", "| total_timesteps | 982500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0692 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196600 |\n", "| time_elapsed | 5298 |\n", "| total_timesteps | 983000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00187 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196700 |\n", "| time_elapsed | 5300 |\n", "| total_timesteps | 983500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.54 |\n", "| value_loss | 0.53 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196800 |\n", "| time_elapsed | 5303 |\n", "| total_timesteps | 984000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.065 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 196900 |\n", "| time_elapsed | 5306 |\n", "| total_timesteps | 984500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0526 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197000 |\n", "| time_elapsed | 5308 |\n", "| total_timesteps | 985000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0412 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197100 |\n", "| time_elapsed | 5311 |\n", "| total_timesteps | 985500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.932 |\n", "| value_loss | 1.27 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197200 |\n", "| time_elapsed | 5313 |\n", "| total_timesteps | 986000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197300 |\n", "| time_elapsed | 5316 |\n", "| total_timesteps | 986500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197400 |\n", "| time_elapsed | 5319 |\n", "| total_timesteps | 987000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.398 |\n", "| value_loss | 0.175 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197500 |\n", "| time_elapsed | 5321 |\n", "| total_timesteps | 987500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00203 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197600 |\n", "| time_elapsed | 5324 |\n", "| total_timesteps | 988000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0581 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197700 |\n", "| time_elapsed | 5326 |\n", "| total_timesteps | 988500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197800 |\n", "| time_elapsed | 5329 |\n", "| total_timesteps | 989000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.496 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 197900 |\n", "| time_elapsed | 5332 |\n", "| total_timesteps | 989500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0596 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198000 |\n", "| time_elapsed | 5334 |\n", "| total_timesteps | 990000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0666 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198100 |\n", "| time_elapsed | 5337 |\n", "| total_timesteps | 990500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0478 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198200 |\n", "| time_elapsed | 5339 |\n", "| total_timesteps | 991000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198300 |\n", "| time_elapsed | 5342 |\n", "| total_timesteps | 991500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0416 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198400 |\n", "| time_elapsed | 5345 |\n", "| total_timesteps | 992000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0503 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198500 |\n", "| time_elapsed | 5347 |\n", "| total_timesteps | 992500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198600 |\n", "| time_elapsed | 5350 |\n", "| total_timesteps | 993000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0523 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198700 |\n", "| time_elapsed | 5352 |\n", "| total_timesteps | 993500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00193 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198800 |\n", "| time_elapsed | 5355 |\n", "| total_timesteps | 994000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 198900 |\n", "| time_elapsed | 5358 |\n", "| total_timesteps | 994500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.045 |\n", "| value_loss | 0.00168 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199000 |\n", "| time_elapsed | 5360 |\n", "| total_timesteps | 995000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.145 |\n", "| value_loss | 0.177 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199100 |\n", "| time_elapsed | 5363 |\n", "| total_timesteps | 995500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.359 |\n", "| value_loss | 0.353 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199200 |\n", "| time_elapsed | 5365 |\n", "| total_timesteps | 996000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.291 |\n", "| value_loss | 0.319 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199300 |\n", "| time_elapsed | 5368 |\n", "| total_timesteps | 996500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199400 |\n", "| time_elapsed | 5371 |\n", "| total_timesteps | 997000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.741 |\n", "| value_loss | 0.709 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199500 |\n", "| time_elapsed | 5373 |\n", "| total_timesteps | 997500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0382 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199600 |\n", "| time_elapsed | 5376 |\n", "| total_timesteps | 998000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199700 |\n", "| time_elapsed | 5379 |\n", "| total_timesteps | 998500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.0019 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199800 |\n", "| time_elapsed | 5381 |\n", "| total_timesteps | 999000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0643 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 199900 |\n", "| time_elapsed | 5384 |\n", "| total_timesteps | 999500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200000 |\n", "| time_elapsed | 5386 |\n", "| total_timesteps | 1000000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.577 |\n", "| value_loss | 0.35 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200100 |\n", "| time_elapsed | 5389 |\n", "| total_timesteps | 1000500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200200 |\n", "| time_elapsed | 5391 |\n", "| total_timesteps | 1001000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.47 |\n", "| value_loss | 0.523 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200300 |\n", "| time_elapsed | 5394 |\n", "| total_timesteps | 1001500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200400 |\n", "| time_elapsed | 5397 |\n", "| total_timesteps | 1002000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.043 |\n", "| value_loss | 0.00209 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200500 |\n", "| time_elapsed | 5399 |\n", "| total_timesteps | 1002500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0445 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200600 |\n", "| time_elapsed | 5402 |\n", "| total_timesteps | 1003000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0701 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200700 |\n", "| time_elapsed | 5404 |\n", "| total_timesteps | 1003500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200800 |\n", "| time_elapsed | 5407 |\n", "| total_timesteps | 1004000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.043 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 200900 |\n", "| time_elapsed | 5409 |\n", "| total_timesteps | 1004500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201000 |\n", "| time_elapsed | 5412 |\n", "| total_timesteps | 1005000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0528 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201100 |\n", "| time_elapsed | 5415 |\n", "| total_timesteps | 1005500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.182 |\n", "| value_loss | 0.175 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201200 |\n", "| time_elapsed | 5417 |\n", "| total_timesteps | 1006000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201300 |\n", "| time_elapsed | 5420 |\n", "| total_timesteps | 1006500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0655 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201400 |\n", "| time_elapsed | 5422 |\n", "| total_timesteps | 1007000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201500 |\n", "| time_elapsed | 5425 |\n", "| total_timesteps | 1007500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201600 |\n", "| time_elapsed | 5427 |\n", "| total_timesteps | 1008000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0427 |\n", "| value_loss | 0.00174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201700 |\n", "| time_elapsed | 5430 |\n", "| total_timesteps | 1008500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201800 |\n", "| time_elapsed | 5432 |\n", "| total_timesteps | 1009000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0333 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 201900 |\n", "| time_elapsed | 5435 |\n", "| total_timesteps | 1009500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00169 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202000 |\n", "| time_elapsed | 5438 |\n", "| total_timesteps | 1010000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00173 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202100 |\n", "| time_elapsed | 5440 |\n", "| total_timesteps | 1010500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | nan |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.26 |\n", "| value_loss | 1.56 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202200 |\n", "| time_elapsed | 5443 |\n", "| total_timesteps | 1011000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202300 |\n", "| time_elapsed | 5445 |\n", "| total_timesteps | 1011500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0505 |\n", "| value_loss | 0.00167 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202400 |\n", "| time_elapsed | 5448 |\n", "| total_timesteps | 1012000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0599 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202500 |\n", "| time_elapsed | 5451 |\n", "| total_timesteps | 1012500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202600 |\n", "| time_elapsed | 5453 |\n", "| total_timesteps | 1013000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202700 |\n", "| time_elapsed | 5456 |\n", "| total_timesteps | 1013500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202800 |\n", "| time_elapsed | 5459 |\n", "| total_timesteps | 1014000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 202900 |\n", "| time_elapsed | 5461 |\n", "| total_timesteps | 1014500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203000 |\n", "| time_elapsed | 5464 |\n", "| total_timesteps | 1015000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203100 |\n", "| time_elapsed | 5466 |\n", "| total_timesteps | 1015500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.053 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203200 |\n", "| time_elapsed | 5469 |\n", "| total_timesteps | 1016000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203300 |\n", "| time_elapsed | 5472 |\n", "| total_timesteps | 1016500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0548 |\n", "| value_loss | 0.0019 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203400 |\n", "| time_elapsed | 5474 |\n", "| total_timesteps | 1017000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0427 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203500 |\n", "| time_elapsed | 5477 |\n", "| total_timesteps | 1017500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.00179 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203600 |\n", "| time_elapsed | 5479 |\n", "| total_timesteps | 1018000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.47 |\n", "| value_loss | 1.45 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203700 |\n", "| time_elapsed | 5482 |\n", "| total_timesteps | 1018500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0445 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203800 |\n", "| time_elapsed | 5485 |\n", "| total_timesteps | 1019000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00157 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 203900 |\n", "| time_elapsed | 5487 |\n", "| total_timesteps | 1019500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.00143 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204000 |\n", "| time_elapsed | 5490 |\n", "| total_timesteps | 1020000 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00145 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204100 |\n", "| time_elapsed | 5492 |\n", "| total_timesteps | 1020500 |\n", "| train/ | |\n", "| entropy_loss | -1.31 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00151 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204200 |\n", "| time_elapsed | 5495 |\n", "| total_timesteps | 1021000 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00154 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204300 |\n", "| time_elapsed | 5498 |\n", "| total_timesteps | 1021500 |\n", "| train/ | |\n", "| entropy_loss | -1.3 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.11 |\n", "| value_loss | 0.712 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204400 |\n", "| time_elapsed | 5500 |\n", "| total_timesteps | 1022000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0481 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204500 |\n", "| time_elapsed | 5503 |\n", "| total_timesteps | 1022500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204600 |\n", "| time_elapsed | 5505 |\n", "| total_timesteps | 1023000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00172 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204700 |\n", "| time_elapsed | 5508 |\n", "| total_timesteps | 1023500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0489 |\n", "| value_loss | 0.00178 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204800 |\n", "| time_elapsed | 5511 |\n", "| total_timesteps | 1024000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.371 |\n", "| value_loss | 0.351 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 204900 |\n", "| time_elapsed | 5513 |\n", "| total_timesteps | 1024500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0524 |\n", "| value_loss | 0.00198 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205000 |\n", "| time_elapsed | 5516 |\n", "| total_timesteps | 1025000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205100 |\n", "| time_elapsed | 5519 |\n", "| total_timesteps | 1025500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205200 |\n", "| time_elapsed | 5521 |\n", "| total_timesteps | 1026000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0693 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205300 |\n", "| time_elapsed | 5524 |\n", "| total_timesteps | 1026500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205400 |\n", "| time_elapsed | 5526 |\n", "| total_timesteps | 1027000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205500 |\n", "| time_elapsed | 5529 |\n", "| total_timesteps | 1027500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0604 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205600 |\n", "| time_elapsed | 5532 |\n", "| total_timesteps | 1028000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205700 |\n", "| time_elapsed | 5534 |\n", "| total_timesteps | 1028500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205800 |\n", "| time_elapsed | 5537 |\n", "| total_timesteps | 1029000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 205900 |\n", "| time_elapsed | 5540 |\n", "| total_timesteps | 1029500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206000 |\n", "| time_elapsed | 5542 |\n", "| total_timesteps | 1030000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206100 |\n", "| time_elapsed | 5545 |\n", "| total_timesteps | 1030500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206200 |\n", "| time_elapsed | 5547 |\n", "| total_timesteps | 1031000 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.00193 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206300 |\n", "| time_elapsed | 5550 |\n", "| total_timesteps | 1031500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206400 |\n", "| time_elapsed | 5553 |\n", "| total_timesteps | 1032000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0493 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206500 |\n", "| time_elapsed | 5555 |\n", "| total_timesteps | 1032500 |\n", "| train/ | |\n", "| entropy_loss | -1.29 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.309 |\n", "| value_loss | 0.351 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206600 |\n", "| time_elapsed | 5558 |\n", "| total_timesteps | 1033000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0576 |\n", "| value_loss | 0.00216 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206700 |\n", "| time_elapsed | 5560 |\n", "| total_timesteps | 1033500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0699 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206800 |\n", "| time_elapsed | 5563 |\n", "| total_timesteps | 1034000 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0513 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 206900 |\n", "| time_elapsed | 5566 |\n", "| total_timesteps | 1034500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0684 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207000 |\n", "| time_elapsed | 5568 |\n", "| total_timesteps | 1035000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207100 |\n", "| time_elapsed | 5571 |\n", "| total_timesteps | 1035500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0452 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207200 |\n", "| time_elapsed | 5573 |\n", "| total_timesteps | 1036000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0611 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207300 |\n", "| time_elapsed | 5576 |\n", "| total_timesteps | 1036500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0682 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207400 |\n", "| time_elapsed | 5578 |\n", "| total_timesteps | 1037000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0687 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207500 |\n", "| time_elapsed | 5581 |\n", "| total_timesteps | 1037500 |\n", "| train/ | |\n", "| entropy_loss | -1.28 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207600 |\n", "| time_elapsed | 5584 |\n", "| total_timesteps | 1038000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0737 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207700 |\n", "| time_elapsed | 5586 |\n", "| total_timesteps | 1038500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207800 |\n", "| time_elapsed | 5589 |\n", "| total_timesteps | 1039000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0468 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 207900 |\n", "| time_elapsed | 5591 |\n", "| total_timesteps | 1039500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0818 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208000 |\n", "| time_elapsed | 5594 |\n", "| total_timesteps | 1040000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.289 |\n", "| value_loss | 0.347 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208100 |\n", "| time_elapsed | 5597 |\n", "| total_timesteps | 1040500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0449 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208200 |\n", "| time_elapsed | 5599 |\n", "| total_timesteps | 1041000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208300 |\n", "| time_elapsed | 5602 |\n", "| total_timesteps | 1041500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.058 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208400 |\n", "| time_elapsed | 5604 |\n", "| total_timesteps | 1042000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208500 |\n", "| time_elapsed | 5607 |\n", "| total_timesteps | 1042500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0646 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208600 |\n", "| time_elapsed | 5609 |\n", "| total_timesteps | 1043000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0659 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208700 |\n", "| time_elapsed | 5612 |\n", "| total_timesteps | 1043500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0483 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208800 |\n", "| time_elapsed | 5615 |\n", "| total_timesteps | 1044000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 208900 |\n", "| time_elapsed | 5617 |\n", "| total_timesteps | 1044500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0567 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209000 |\n", "| time_elapsed | 5620 |\n", "| total_timesteps | 1045000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209100 |\n", "| time_elapsed | 5622 |\n", "| total_timesteps | 1045500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0352 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209200 |\n", "| time_elapsed | 5625 |\n", "| total_timesteps | 1046000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.455 |\n", "| value_loss | 0.523 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209300 |\n", "| time_elapsed | 5628 |\n", "| total_timesteps | 1046500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0656 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209400 |\n", "| time_elapsed | 5630 |\n", "| total_timesteps | 1047000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209500 |\n", "| time_elapsed | 5633 |\n", "| total_timesteps | 1047500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209600 |\n", "| time_elapsed | 5635 |\n", "| total_timesteps | 1048000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0786 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209700 |\n", "| time_elapsed | 5638 |\n", "| total_timesteps | 1048500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209800 |\n", "| time_elapsed | 5641 |\n", "| total_timesteps | 1049000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0681 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 209900 |\n", "| time_elapsed | 5643 |\n", "| total_timesteps | 1049500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.63 |\n", "| value_loss | 1.43 |\n", "------------------------------------\n", "Eval num_timesteps=1050000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1050000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0679 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210000 |\n", "| time_elapsed | 5657 |\n", "| total_timesteps | 1050000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210100 |\n", "| time_elapsed | 5659 |\n", "| total_timesteps | 1050500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210200 |\n", "| time_elapsed | 5662 |\n", "| total_timesteps | 1051000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00265 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210300 |\n", "| time_elapsed | 5664 |\n", "| total_timesteps | 1051500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0856 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210400 |\n", "| time_elapsed | 5667 |\n", "| total_timesteps | 1052000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0741 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210500 |\n", "| time_elapsed | 5670 |\n", "| total_timesteps | 1052500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.2 |\n", "| value_loss | 0.696 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210600 |\n", "| time_elapsed | 5672 |\n", "| total_timesteps | 1053000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.283 |\n", "| value_loss | 0.421 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210700 |\n", "| time_elapsed | 5675 |\n", "| total_timesteps | 1053500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.359 |\n", "| value_loss | 0.347 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210800 |\n", "| time_elapsed | 5677 |\n", "| total_timesteps | 1054000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.507 |\n", "| value_loss | 0.513 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 210900 |\n", "| time_elapsed | 5680 |\n", "| total_timesteps | 1054500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0381 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211000 |\n", "| time_elapsed | 5683 |\n", "| total_timesteps | 1055000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211100 |\n", "| time_elapsed | 5685 |\n", "| total_timesteps | 1055500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211200 |\n", "| time_elapsed | 5688 |\n", "| total_timesteps | 1056000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0728 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211300 |\n", "| time_elapsed | 5690 |\n", "| total_timesteps | 1056500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0424 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211400 |\n", "| time_elapsed | 5693 |\n", "| total_timesteps | 1057000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211500 |\n", "| time_elapsed | 5696 |\n", "| total_timesteps | 1057500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.064 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211600 |\n", "| time_elapsed | 5698 |\n", "| total_timesteps | 1058000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0768 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211700 |\n", "| time_elapsed | 5701 |\n", "| total_timesteps | 1058500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.825 |\n", "| value_loss | 1.44 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211800 |\n", "| time_elapsed | 5704 |\n", "| total_timesteps | 1059000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.0025 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 211900 |\n", "| time_elapsed | 5706 |\n", "| total_timesteps | 1059500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0584 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212000 |\n", "| time_elapsed | 5709 |\n", "| total_timesteps | 1060000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212100 |\n", "| time_elapsed | 5711 |\n", "| total_timesteps | 1060500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.046 |\n", "| value_loss | 0.0026 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212200 |\n", "| time_elapsed | 5714 |\n", "| total_timesteps | 1061000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0726 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212300 |\n", "| time_elapsed | 5716 |\n", "| total_timesteps | 1061500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00276 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212400 |\n", "| time_elapsed | 5719 |\n", "| total_timesteps | 1062000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.071 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212500 |\n", "| time_elapsed | 5722 |\n", "| total_timesteps | 1062500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00276 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212600 |\n", "| time_elapsed | 5724 |\n", "| total_timesteps | 1063000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.514 |\n", "| value_loss | 0.341 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212700 |\n", "| time_elapsed | 5727 |\n", "| total_timesteps | 1063500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.746 |\n", "| value_loss | 0.515 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212800 |\n", "| time_elapsed | 5729 |\n", "| total_timesteps | 1064000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.131 |\n", "| value_loss | 0.171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 212900 |\n", "| time_elapsed | 5732 |\n", "| total_timesteps | 1064500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0698 |\n", "| value_loss | 0.00276 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213000 |\n", "| time_elapsed | 5735 |\n", "| total_timesteps | 1065000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0649 |\n", "| value_loss | 0.0028 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213100 |\n", "| time_elapsed | 5737 |\n", "| total_timesteps | 1065500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.064 |\n", "| value_loss | 0.00304 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213200 |\n", "| time_elapsed | 5740 |\n", "| total_timesteps | 1066000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00283 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213300 |\n", "| time_elapsed | 5742 |\n", "| total_timesteps | 1066500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.934 |\n", "| value_loss | 1.54 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213400 |\n", "| time_elapsed | 5745 |\n", "| total_timesteps | 1067000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213500 |\n", "| time_elapsed | 5747 |\n", "| total_timesteps | 1067500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0562 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213600 |\n", "| time_elapsed | 5750 |\n", "| total_timesteps | 1068000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0827 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213700 |\n", "| time_elapsed | 5753 |\n", "| total_timesteps | 1068500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0642 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213800 |\n", "| time_elapsed | 5755 |\n", "| total_timesteps | 1069000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00262 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 213900 |\n", "| time_elapsed | 5758 |\n", "| total_timesteps | 1069500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0541 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214000 |\n", "| time_elapsed | 5760 |\n", "| total_timesteps | 1070000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214100 |\n", "| time_elapsed | 5763 |\n", "| total_timesteps | 1070500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214200 |\n", "| time_elapsed | 5766 |\n", "| total_timesteps | 1071000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00254 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214300 |\n", "| time_elapsed | 5768 |\n", "| total_timesteps | 1071500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214400 |\n", "| time_elapsed | 5771 |\n", "| total_timesteps | 1072000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.14 |\n", "| value_loss | 1.43 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214500 |\n", "| time_elapsed | 5773 |\n", "| total_timesteps | 1072500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214600 |\n", "| time_elapsed | 5776 |\n", "| total_timesteps | 1073000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214700 |\n", "| time_elapsed | 5778 |\n", "| total_timesteps | 1073500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214800 |\n", "| time_elapsed | 5781 |\n", "| total_timesteps | 1074000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 214900 |\n", "| time_elapsed | 5784 |\n", "| total_timesteps | 1074500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215000 |\n", "| time_elapsed | 5786 |\n", "| total_timesteps | 1075000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0664 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215100 |\n", "| time_elapsed | 5789 |\n", "| total_timesteps | 1075500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215200 |\n", "| time_elapsed | 5791 |\n", "| total_timesteps | 1076000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.606 |\n", "| value_loss | 0.344 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215300 |\n", "| time_elapsed | 5794 |\n", "| total_timesteps | 1076500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0708 |\n", "| value_loss | 0.00275 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215400 |\n", "| time_elapsed | 5797 |\n", "| total_timesteps | 1077000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0538 |\n", "| value_loss | 0.00294 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215500 |\n", "| time_elapsed | 5799 |\n", "| total_timesteps | 1077500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0632 |\n", "| value_loss | 0.00295 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215600 |\n", "| time_elapsed | 5802 |\n", "| total_timesteps | 1078000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.07 |\n", "| value_loss | 0.688 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215700 |\n", "| time_elapsed | 5804 |\n", "| total_timesteps | 1078500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0835 |\n", "| value_loss | 0.00307 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215800 |\n", "| time_elapsed | 5807 |\n", "| total_timesteps | 1079000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.836 |\n", "| value_loss | 0.69 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 215900 |\n", "| time_elapsed | 5809 |\n", "| total_timesteps | 1079500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00285 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216000 |\n", "| time_elapsed | 5812 |\n", "| total_timesteps | 1080000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 0.87 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216100 |\n", "| time_elapsed | 5815 |\n", "| total_timesteps | 1080500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216200 |\n", "| time_elapsed | 5817 |\n", "| total_timesteps | 1081000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.00279 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216300 |\n", "| time_elapsed | 5820 |\n", "| total_timesteps | 1081500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.003 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216400 |\n", "| time_elapsed | 5823 |\n", "| total_timesteps | 1082000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00294 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216500 |\n", "| time_elapsed | 5825 |\n", "| total_timesteps | 1082500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.934 |\n", "| value_loss | 0.691 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216600 |\n", "| time_elapsed | 5828 |\n", "| total_timesteps | 1083000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.315 |\n", "| value_loss | 0.172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216700 |\n", "| time_elapsed | 5830 |\n", "| total_timesteps | 1083500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0458 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216800 |\n", "| time_elapsed | 5833 |\n", "| total_timesteps | 1084000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.312 |\n", "| value_loss | 0.171 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 216900 |\n", "| time_elapsed | 5835 |\n", "| total_timesteps | 1084500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.0027 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217000 |\n", "| time_elapsed | 5838 |\n", "| total_timesteps | 1085000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0588 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217100 |\n", "| time_elapsed | 5840 |\n", "| total_timesteps | 1085500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.975 |\n", "| value_loss | 0.516 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217200 |\n", "| time_elapsed | 5843 |\n", "| total_timesteps | 1086000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.24 |\n", "| value_loss | 0.872 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217300 |\n", "| time_elapsed | 5846 |\n", "| total_timesteps | 1086500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.123 |\n", "| value_loss | 0.172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217400 |\n", "| time_elapsed | 5848 |\n", "| total_timesteps | 1087000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00275 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217500 |\n", "| time_elapsed | 5851 |\n", "| total_timesteps | 1087500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00265 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217600 |\n", "| time_elapsed | 5854 |\n", "| total_timesteps | 1088000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0558 |\n", "| value_loss | 0.00247 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217700 |\n", "| time_elapsed | 5856 |\n", "| total_timesteps | 1088500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00261 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217800 |\n", "| time_elapsed | 5859 |\n", "| total_timesteps | 1089000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0556 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 217900 |\n", "| time_elapsed | 5861 |\n", "| total_timesteps | 1089500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0612 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218000 |\n", "| time_elapsed | 5864 |\n", "| total_timesteps | 1090000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0977 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218100 |\n", "| time_elapsed | 5867 |\n", "| total_timesteps | 1090500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0665 |\n", "| value_loss | 0.00254 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218200 |\n", "| time_elapsed | 5869 |\n", "| total_timesteps | 1091000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.657 |\n", "| value_loss | 0.52 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218300 |\n", "| time_elapsed | 5872 |\n", "| total_timesteps | 1091500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.078 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218400 |\n", "| time_elapsed | 5874 |\n", "| total_timesteps | 1092000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.068 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218500 |\n", "| time_elapsed | 5877 |\n", "| total_timesteps | 1092500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.32 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218600 |\n", "| time_elapsed | 5879 |\n", "| total_timesteps | 1093000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.04 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218700 |\n", "| time_elapsed | 5882 |\n", "| total_timesteps | 1093500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218800 |\n", "| time_elapsed | 5885 |\n", "| total_timesteps | 1094000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 218900 |\n", "| time_elapsed | 5887 |\n", "| total_timesteps | 1094500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219000 |\n", "| time_elapsed | 5890 |\n", "| total_timesteps | 1095000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0595 |\n", "| value_loss | 0.0025 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219100 |\n", "| time_elapsed | 5892 |\n", "| total_timesteps | 1095500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.575 |\n", "| value_loss | 0.517 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219200 |\n", "| time_elapsed | 5895 |\n", "| total_timesteps | 1096000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219300 |\n", "| time_elapsed | 5897 |\n", "| total_timesteps | 1096500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.554 |\n", "| value_loss | 0.344 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219400 |\n", "| time_elapsed | 5900 |\n", "| total_timesteps | 1097000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219500 |\n", "| time_elapsed | 5902 |\n", "| total_timesteps | 1097500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219600 |\n", "| time_elapsed | 5905 |\n", "| total_timesteps | 1098000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219700 |\n", "| time_elapsed | 5908 |\n", "| total_timesteps | 1098500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219800 |\n", "| time_elapsed | 5910 |\n", "| total_timesteps | 1099000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0734 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 219900 |\n", "| time_elapsed | 5913 |\n", "| total_timesteps | 1099500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220000 |\n", "| time_elapsed | 5915 |\n", "| total_timesteps | 1100000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220100 |\n", "| time_elapsed | 5918 |\n", "| total_timesteps | 1100500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220200 |\n", "| time_elapsed | 5920 |\n", "| total_timesteps | 1101000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0616 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220300 |\n", "| time_elapsed | 5923 |\n", "| total_timesteps | 1101500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00255 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220400 |\n", "| time_elapsed | 5926 |\n", "| total_timesteps | 1102000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.791 |\n", "| value_loss | 0.693 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220500 |\n", "| time_elapsed | 5928 |\n", "| total_timesteps | 1102500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.835 |\n", "| value_loss | 0.695 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220600 |\n", "| time_elapsed | 5931 |\n", "| total_timesteps | 1103000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.86 |\n", "| value_loss | 0.876 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220700 |\n", "| time_elapsed | 5933 |\n", "| total_timesteps | 1103500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.769 |\n", "| value_loss | 0.52 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220800 |\n", "| time_elapsed | 5936 |\n", "| total_timesteps | 1104000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.356 |\n", "| value_loss | 0.346 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 220900 |\n", "| time_elapsed | 5939 |\n", "| total_timesteps | 1104500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.064 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221000 |\n", "| time_elapsed | 5941 |\n", "| total_timesteps | 1105000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.3 |\n", "| value_loss | 1.43 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221100 |\n", "| time_elapsed | 5944 |\n", "| total_timesteps | 1105500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0612 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221200 |\n", "| time_elapsed | 5946 |\n", "| total_timesteps | 1106000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221300 |\n", "| time_elapsed | 5949 |\n", "| total_timesteps | 1106500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.795 |\n", "| value_loss | 0.7 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221400 |\n", "| time_elapsed | 5951 |\n", "| total_timesteps | 1107000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.71 |\n", "| value_loss | 2.38 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221500 |\n", "| time_elapsed | 5954 |\n", "| total_timesteps | 1107500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0703 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221600 |\n", "| time_elapsed | 5957 |\n", "| total_timesteps | 1108000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0625 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221700 |\n", "| time_elapsed | 5959 |\n", "| total_timesteps | 1108500 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 221800 |\n", "| time_elapsed | 5962 |\n", "| total_timesteps | 1109000 |\n", "| train/ | |\n", "| entropy_loss | -1.27 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.17 |\n", "| value_loss | 1.26 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 221900 |\n", "| time_elapsed | 5964 |\n", "| total_timesteps | 1109500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222000 |\n", "| time_elapsed | 5967 |\n", "| total_timesteps | 1110000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0613 |\n", "| value_loss | 0.00248 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222100 |\n", "| time_elapsed | 5970 |\n", "| total_timesteps | 1110500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.16 |\n", "| value_loss | 0.874 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222200 |\n", "| time_elapsed | 5972 |\n", "| total_timesteps | 1111000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222300 |\n", "| time_elapsed | 5975 |\n", "| total_timesteps | 1111500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00268 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222400 |\n", "| time_elapsed | 5977 |\n", "| total_timesteps | 1112000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222500 |\n", "| time_elapsed | 5980 |\n", "| total_timesteps | 1112500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0662 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222600 |\n", "| time_elapsed | 5983 |\n", "| total_timesteps | 1113000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0704 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222700 |\n", "| time_elapsed | 5985 |\n", "| total_timesteps | 1113500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0477 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222800 |\n", "| time_elapsed | 5988 |\n", "| total_timesteps | 1114000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0697 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 222900 |\n", "| time_elapsed | 5990 |\n", "| total_timesteps | 1114500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.344 |\n", "| value_loss | 0.172 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223000 |\n", "| time_elapsed | 5993 |\n", "| total_timesteps | 1115000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.073 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223100 |\n", "| time_elapsed | 5996 |\n", "| total_timesteps | 1115500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0508 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223200 |\n", "| time_elapsed | 5998 |\n", "| total_timesteps | 1116000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.29 |\n", "| value_loss | 1.43 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223300 |\n", "| time_elapsed | 6001 |\n", "| total_timesteps | 1116500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223400 |\n", "| time_elapsed | 6003 |\n", "| total_timesteps | 1117000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0748 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223500 |\n", "| time_elapsed | 6006 |\n", "| total_timesteps | 1117500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223600 |\n", "| time_elapsed | 6009 |\n", "| total_timesteps | 1118000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00241 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223700 |\n", "| time_elapsed | 6011 |\n", "| total_timesteps | 1118500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0667 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223800 |\n", "| time_elapsed | 6014 |\n", "| total_timesteps | 1119000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 223900 |\n", "| time_elapsed | 6016 |\n", "| total_timesteps | 1119500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.124 |\n", "| value_loss | 0.172 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224000 |\n", "| time_elapsed | 6019 |\n", "| total_timesteps | 1120000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224100 |\n", "| time_elapsed | 6021 |\n", "| total_timesteps | 1120500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0643 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224200 |\n", "| time_elapsed | 6024 |\n", "| total_timesteps | 1121000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224300 |\n", "| time_elapsed | 6026 |\n", "| total_timesteps | 1121500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0607 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224400 |\n", "| time_elapsed | 6029 |\n", "| total_timesteps | 1122000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224500 |\n", "| time_elapsed | 6032 |\n", "| total_timesteps | 1122500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224600 |\n", "| time_elapsed | 6034 |\n", "| total_timesteps | 1123000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0587 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224700 |\n", "| time_elapsed | 6037 |\n", "| total_timesteps | 1123500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224800 |\n", "| time_elapsed | 6039 |\n", "| total_timesteps | 1124000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 224900 |\n", "| time_elapsed | 6042 |\n", "| total_timesteps | 1124500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00268 |\n", "------------------------------------\n", "Eval num_timesteps=1125000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1125000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0505 |\n", "| value_loss | 0.00282 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225000 |\n", "| time_elapsed | 6056 |\n", "| total_timesteps | 1125000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225100 |\n", "| time_elapsed | 6061 |\n", "| total_timesteps | 1125500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225200 |\n", "| time_elapsed | 6063 |\n", "| total_timesteps | 1126000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0768 |\n", "| value_loss | 0.0028 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225300 |\n", "| time_elapsed | 6066 |\n", "| total_timesteps | 1126500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.11 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225400 |\n", "| time_elapsed | 6069 |\n", "| total_timesteps | 1127000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00275 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225500 |\n", "| time_elapsed | 6071 |\n", "| total_timesteps | 1127500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0623 |\n", "| value_loss | 0.00267 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225600 |\n", "| time_elapsed | 6074 |\n", "| total_timesteps | 1128000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0676 |\n", "| value_loss | 0.00298 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225700 |\n", "| time_elapsed | 6076 |\n", "| total_timesteps | 1128500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.061 |\n", "| value_loss | 0.00297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225800 |\n", "| time_elapsed | 6079 |\n", "| total_timesteps | 1129000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0632 |\n", "| value_loss | 0.00298 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 225900 |\n", "| time_elapsed | 6081 |\n", "| total_timesteps | 1129500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.485 |\n", "| value_loss | 0.512 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226000 |\n", "| time_elapsed | 6084 |\n", "| total_timesteps | 1130000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0712 |\n", "| value_loss | 0.00303 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226100 |\n", "| time_elapsed | 6087 |\n", "| total_timesteps | 1130500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0774 |\n", "| value_loss | 0.00297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226200 |\n", "| time_elapsed | 6089 |\n", "| total_timesteps | 1131000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00301 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226300 |\n", "| time_elapsed | 6092 |\n", "| total_timesteps | 1131500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0537 |\n", "| value_loss | 0.00293 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226400 |\n", "| time_elapsed | 6094 |\n", "| total_timesteps | 1132000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00273 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226500 |\n", "| time_elapsed | 6097 |\n", "| total_timesteps | 1132500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.969 |\n", "| value_loss | 1.54 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226600 |\n", "| time_elapsed | 6099 |\n", "| total_timesteps | 1133000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.55 |\n", "| value_loss | 0.874 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226700 |\n", "| time_elapsed | 6102 |\n", "| total_timesteps | 1133500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.04 |\n", "| value_loss | 2.54 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226800 |\n", "| time_elapsed | 6105 |\n", "| total_timesteps | 1134000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0846 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 226900 |\n", "| time_elapsed | 6107 |\n", "| total_timesteps | 1134500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0538 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227000 |\n", "| time_elapsed | 6110 |\n", "| total_timesteps | 1135000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227100 |\n", "| time_elapsed | 6112 |\n", "| total_timesteps | 1135500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.597 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227200 |\n", "| time_elapsed | 6115 |\n", "| total_timesteps | 1136000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227300 |\n", "| time_elapsed | 6118 |\n", "| total_timesteps | 1136500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0729 |\n", "| value_loss | 0.00236 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227400 |\n", "| time_elapsed | 6120 |\n", "| total_timesteps | 1137000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | nan |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.68 |\n", "| value_loss | 2.17 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227500 |\n", "| time_elapsed | 6123 |\n", "| total_timesteps | 1137500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227600 |\n", "| time_elapsed | 6125 |\n", "| total_timesteps | 1138000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0574 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227700 |\n", "| time_elapsed | 6128 |\n", "| total_timesteps | 1138500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0736 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227800 |\n", "| time_elapsed | 6130 |\n", "| total_timesteps | 1139000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0379 |\n", "| value_loss | 0.00246 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 227900 |\n", "| time_elapsed | 6133 |\n", "| total_timesteps | 1139500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.095 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228000 |\n", "| time_elapsed | 6136 |\n", "| total_timesteps | 1140000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0486 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228100 |\n", "| time_elapsed | 6138 |\n", "| total_timesteps | 1140500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.00237 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228200 |\n", "| time_elapsed | 6141 |\n", "| total_timesteps | 1141000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00243 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228300 |\n", "| time_elapsed | 6143 |\n", "| total_timesteps | 1141500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0597 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228400 |\n", "| time_elapsed | 6146 |\n", "| total_timesteps | 1142000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228500 |\n", "| time_elapsed | 6148 |\n", "| total_timesteps | 1142500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228600 |\n", "| time_elapsed | 6151 |\n", "| total_timesteps | 1143000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228700 |\n", "| time_elapsed | 6154 |\n", "| total_timesteps | 1143500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.061 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228800 |\n", "| time_elapsed | 6156 |\n", "| total_timesteps | 1144000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0388 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 228900 |\n", "| time_elapsed | 6159 |\n", "| total_timesteps | 1144500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0578 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229000 |\n", "| time_elapsed | 6161 |\n", "| total_timesteps | 1145000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0526 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229100 |\n", "| time_elapsed | 6164 |\n", "| total_timesteps | 1145500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229200 |\n", "| time_elapsed | 6166 |\n", "| total_timesteps | 1146000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229300 |\n", "| time_elapsed | 6169 |\n", "| total_timesteps | 1146500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.938 |\n", "| value_loss | 0.524 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229400 |\n", "| time_elapsed | 6172 |\n", "| total_timesteps | 1147000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229500 |\n", "| time_elapsed | 6174 |\n", "| total_timesteps | 1147500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229600 |\n", "| time_elapsed | 6177 |\n", "| total_timesteps | 1148000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229700 |\n", "| time_elapsed | 6179 |\n", "| total_timesteps | 1148500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0314 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229800 |\n", "| time_elapsed | 6182 |\n", "| total_timesteps | 1149000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 229900 |\n", "| time_elapsed | 6185 |\n", "| total_timesteps | 1149500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0465 |\n", "| value_loss | 0.00218 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230000 |\n", "| time_elapsed | 6187 |\n", "| total_timesteps | 1150000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0464 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230100 |\n", "| time_elapsed | 6190 |\n", "| total_timesteps | 1150500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0502 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230200 |\n", "| time_elapsed | 6192 |\n", "| total_timesteps | 1151000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230300 |\n", "| time_elapsed | 6195 |\n", "| total_timesteps | 1151500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230400 |\n", "| time_elapsed | 6197 |\n", "| total_timesteps | 1152000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0725 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230500 |\n", "| time_elapsed | 6200 |\n", "| total_timesteps | 1152500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0835 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230600 |\n", "| time_elapsed | 6202 |\n", "| total_timesteps | 1153000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.00263 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230700 |\n", "| time_elapsed | 6205 |\n", "| total_timesteps | 1153500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230800 |\n", "| time_elapsed | 6207 |\n", "| total_timesteps | 1154000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.049 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 230900 |\n", "| time_elapsed | 6210 |\n", "| total_timesteps | 1154500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0487 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231000 |\n", "| time_elapsed | 6213 |\n", "| total_timesteps | 1155000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0648 |\n", "| value_loss | 0.00268 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231100 |\n", "| time_elapsed | 6215 |\n", "| total_timesteps | 1155500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0542 |\n", "| value_loss | 0.00273 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231200 |\n", "| time_elapsed | 6218 |\n", "| total_timesteps | 1156000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231300 |\n", "| time_elapsed | 6220 |\n", "| total_timesteps | 1156500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.55 |\n", "| value_loss | 1.25 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231400 |\n", "| time_elapsed | 6223 |\n", "| total_timesteps | 1157000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231500 |\n", "| time_elapsed | 6226 |\n", "| total_timesteps | 1157500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231600 |\n", "| time_elapsed | 6228 |\n", "| total_timesteps | 1158000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0684 |\n", "| value_loss | 0.0026 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231700 |\n", "| time_elapsed | 6231 |\n", "| total_timesteps | 1158500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.425 |\n", "| value_loss | 0.345 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231800 |\n", "| time_elapsed | 6233 |\n", "| total_timesteps | 1159000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 231900 |\n", "| time_elapsed | 6236 |\n", "| total_timesteps | 1159500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0731 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232000 |\n", "| time_elapsed | 6238 |\n", "| total_timesteps | 1160000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232100 |\n", "| time_elapsed | 6241 |\n", "| total_timesteps | 1160500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232200 |\n", "| time_elapsed | 6244 |\n", "| total_timesteps | 1161000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.066 |\n", "| value_loss | 0.00251 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232300 |\n", "| time_elapsed | 6246 |\n", "| total_timesteps | 1161500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232400 |\n", "| time_elapsed | 6249 |\n", "| total_timesteps | 1162000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232500 |\n", "| time_elapsed | 6251 |\n", "| total_timesteps | 1162500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0372 |\n", "| value_loss | 0.00276 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232600 |\n", "| time_elapsed | 6254 |\n", "| total_timesteps | 1163000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.31 |\n", "| value_loss | 3.1 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232700 |\n", "| time_elapsed | 6257 |\n", "| total_timesteps | 1163500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0734 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232800 |\n", "| time_elapsed | 6259 |\n", "| total_timesteps | 1164000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.0026 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 232900 |\n", "| time_elapsed | 6262 |\n", "| total_timesteps | 1164500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0918 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233000 |\n", "| time_elapsed | 6264 |\n", "| total_timesteps | 1165000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.054 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233100 |\n", "| time_elapsed | 6267 |\n", "| total_timesteps | 1165500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233200 |\n", "| time_elapsed | 6269 |\n", "| total_timesteps | 1166000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0349 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233300 |\n", "| time_elapsed | 6272 |\n", "| total_timesteps | 1166500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233400 |\n", "| time_elapsed | 6275 |\n", "| total_timesteps | 1167000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0574 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233500 |\n", "| time_elapsed | 6277 |\n", "| total_timesteps | 1167500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0548 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233600 |\n", "| time_elapsed | 6280 |\n", "| total_timesteps | 1168000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233700 |\n", "| time_elapsed | 6283 |\n", "| total_timesteps | 1168500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.34 |\n", "| value_loss | 0.875 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233800 |\n", "| time_elapsed | 6285 |\n", "| total_timesteps | 1169000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 233900 |\n", "| time_elapsed | 6288 |\n", "| total_timesteps | 1169500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0518 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 234000 |\n", "| time_elapsed | 6290 |\n", "| total_timesteps | 1170000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.819 |\n", "| value_loss | 0.52 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 234100 |\n", "| time_elapsed | 6293 |\n", "| total_timesteps | 1170500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.672 |\n", "| value_loss | 0.517 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 234200 |\n", "| time_elapsed | 6295 |\n", "| total_timesteps | 1171000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 234300 |\n", "| time_elapsed | 6298 |\n", "| total_timesteps | 1171500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0906 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234400 |\n", "| time_elapsed | 6300 |\n", "| total_timesteps | 1172000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.05 |\n", "| value_loss | 0.908 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234500 |\n", "| time_elapsed | 6303 |\n", "| total_timesteps | 1172500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0889 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234600 |\n", "| time_elapsed | 6306 |\n", "| total_timesteps | 1173000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0557 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234700 |\n", "| time_elapsed | 6308 |\n", "| total_timesteps | 1173500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0925 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234800 |\n", "| time_elapsed | 6311 |\n", "| total_timesteps | 1174000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00261 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 234900 |\n", "| time_elapsed | 6313 |\n", "| total_timesteps | 1174500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0498 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235000 |\n", "| time_elapsed | 6316 |\n", "| total_timesteps | 1175000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0629 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235100 |\n", "| time_elapsed | 6318 |\n", "| total_timesteps | 1175500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.066 |\n", "| value_loss | 0.00277 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235200 |\n", "| time_elapsed | 6321 |\n", "| total_timesteps | 1176000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0602 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235300 |\n", "| time_elapsed | 6324 |\n", "| total_timesteps | 1176500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.14 |\n", "| value_loss | 3.1 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235400 |\n", "| time_elapsed | 6326 |\n", "| total_timesteps | 1177000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0761 |\n", "| value_loss | 0.00269 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235500 |\n", "| time_elapsed | 6329 |\n", "| total_timesteps | 1177500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235600 |\n", "| time_elapsed | 6331 |\n", "| total_timesteps | 1178000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0426 |\n", "| value_loss | 0.00259 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235700 |\n", "| time_elapsed | 6334 |\n", "| total_timesteps | 1178500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00285 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235800 |\n", "| time_elapsed | 6337 |\n", "| total_timesteps | 1179000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.0029 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 235900 |\n", "| time_elapsed | 6339 |\n", "| total_timesteps | 1179500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.856 |\n", "| value_loss | 0.513 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236000 |\n", "| time_elapsed | 6342 |\n", "| total_timesteps | 1180000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0832 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236100 |\n", "| time_elapsed | 6344 |\n", "| total_timesteps | 1180500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.03 |\n", "| value_loss | 0.869 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236200 |\n", "| time_elapsed | 6347 |\n", "| total_timesteps | 1181000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00307 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236300 |\n", "| time_elapsed | 6349 |\n", "| total_timesteps | 1181500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0496 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236400 |\n", "| time_elapsed | 6352 |\n", "| total_timesteps | 1182000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0817 |\n", "| value_loss | 0.00293 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236500 |\n", "| time_elapsed | 6355 |\n", "| total_timesteps | 1182500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0747 |\n", "| value_loss | 0.00277 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236600 |\n", "| time_elapsed | 6357 |\n", "| total_timesteps | 1183000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00262 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236700 |\n", "| time_elapsed | 6360 |\n", "| total_timesteps | 1183500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0428 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236800 |\n", "| time_elapsed | 6363 |\n", "| total_timesteps | 1184000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 236900 |\n", "| time_elapsed | 6365 |\n", "| total_timesteps | 1184500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.063 |\n", "| value_loss | 0.0027 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237000 |\n", "| time_elapsed | 6368 |\n", "| total_timesteps | 1185000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.566 |\n", "| value_loss | 0.517 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237100 |\n", "| time_elapsed | 6370 |\n", "| total_timesteps | 1185500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0369 |\n", "| value_loss | 0.00261 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237200 |\n", "| time_elapsed | 6373 |\n", "| total_timesteps | 1186000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.03 |\n", "| value_loss | 0.875 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237300 |\n", "| time_elapsed | 6375 |\n", "| total_timesteps | 1186500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.062 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237400 |\n", "| time_elapsed | 6378 |\n", "| total_timesteps | 1187000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00257 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 20 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237500 |\n", "| time_elapsed | 6381 |\n", "| total_timesteps | 1187500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0602 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237600 |\n", "| time_elapsed | 6383 |\n", "| total_timesteps | 1188000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.078 |\n", "| value_loss | 0.00271 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237700 |\n", "| time_elapsed | 6386 |\n", "| total_timesteps | 1188500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0764 |\n", "| value_loss | 0.00268 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237800 |\n", "| time_elapsed | 6388 |\n", "| total_timesteps | 1189000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 237900 |\n", "| time_elapsed | 6391 |\n", "| total_timesteps | 1189500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.2 |\n", "| value_loss | 0.171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238000 |\n", "| time_elapsed | 6393 |\n", "| total_timesteps | 1190000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.343 |\n", "| value_loss | 0.343 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238100 |\n", "| time_elapsed | 6396 |\n", "| total_timesteps | 1190500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0677 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238200 |\n", "| time_elapsed | 6399 |\n", "| total_timesteps | 1191000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0546 |\n", "| value_loss | 0.00276 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238300 |\n", "| time_elapsed | 6401 |\n", "| total_timesteps | 1191500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0362 |\n", "| value_loss | 0.00265 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238400 |\n", "| time_elapsed | 6404 |\n", "| total_timesteps | 1192000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.263 |\n", "| value_loss | 0.343 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238500 |\n", "| time_elapsed | 6406 |\n", "| total_timesteps | 1192500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0427 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238600 |\n", "| time_elapsed | 6409 |\n", "| total_timesteps | 1193000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.964 |\n", "| value_loss | 1.25 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238700 |\n", "| time_elapsed | 6412 |\n", "| total_timesteps | 1193500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238800 |\n", "| time_elapsed | 6414 |\n", "| total_timesteps | 1194000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0624 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 238900 |\n", "| time_elapsed | 6417 |\n", "| total_timesteps | 1194500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0751 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239000 |\n", "| time_elapsed | 6419 |\n", "| total_timesteps | 1195000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239100 |\n", "| time_elapsed | 6422 |\n", "| total_timesteps | 1195500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.00275 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239200 |\n", "| time_elapsed | 6424 |\n", "| total_timesteps | 1196000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.391 |\n", "| value_loss | 0.343 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239300 |\n", "| time_elapsed | 6427 |\n", "| total_timesteps | 1196500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0648 |\n", "| value_loss | 0.00267 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239400 |\n", "| time_elapsed | 6430 |\n", "| total_timesteps | 1197000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0691 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239500 |\n", "| time_elapsed | 6432 |\n", "| total_timesteps | 1197500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239600 |\n", "| time_elapsed | 6435 |\n", "| total_timesteps | 1198000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.062 |\n", "| value_loss | 0.00272 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239700 |\n", "| time_elapsed | 6437 |\n", "| total_timesteps | 1198500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0427 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239800 |\n", "| time_elapsed | 6440 |\n", "| total_timesteps | 1199000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0467 |\n", "| value_loss | 0.00276 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 239900 |\n", "| time_elapsed | 6443 |\n", "| total_timesteps | 1199500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0705 |\n", "| value_loss | 0.0026 |\n", "------------------------------------\n", "Eval num_timesteps=1200000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1200000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240000 |\n", "| time_elapsed | 6456 |\n", "| total_timesteps | 1200000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240100 |\n", "| time_elapsed | 6458 |\n", "| total_timesteps | 1200500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0541 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240200 |\n", "| time_elapsed | 6461 |\n", "| total_timesteps | 1201000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240300 |\n", "| time_elapsed | 6463 |\n", "| total_timesteps | 1201500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240400 |\n", "| time_elapsed | 6466 |\n", "| total_timesteps | 1202000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.066 |\n", "| value_loss | 0.00253 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240500 |\n", "| time_elapsed | 6469 |\n", "| total_timesteps | 1202500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.26 |\n", "| value_loss | 1.98 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240600 |\n", "| time_elapsed | 6471 |\n", "| total_timesteps | 1203000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.712 |\n", "| value_loss | 0.692 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240700 |\n", "| time_elapsed | 6474 |\n", "| total_timesteps | 1203500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0537 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240800 |\n", "| time_elapsed | 6476 |\n", "| total_timesteps | 1204000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.073 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 240900 |\n", "| time_elapsed | 6479 |\n", "| total_timesteps | 1204500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241000 |\n", "| time_elapsed | 6481 |\n", "| total_timesteps | 1205000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241100 |\n", "| time_elapsed | 6484 |\n", "| total_timesteps | 1205500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0678 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241200 |\n", "| time_elapsed | 6487 |\n", "| total_timesteps | 1206000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.357 |\n", "| value_loss | 0.171 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241300 |\n", "| time_elapsed | 6489 |\n", "| total_timesteps | 1206500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.076 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241400 |\n", "| time_elapsed | 6492 |\n", "| total_timesteps | 1207000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241500 |\n", "| time_elapsed | 6494 |\n", "| total_timesteps | 1207500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.003 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241600 |\n", "| time_elapsed | 6497 |\n", "| total_timesteps | 1208000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241700 |\n", "| time_elapsed | 6500 |\n", "| total_timesteps | 1208500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241800 |\n", "| time_elapsed | 6502 |\n", "| total_timesteps | 1209000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0524 |\n", "| value_loss | 0.00262 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 241900 |\n", "| time_elapsed | 6505 |\n", "| total_timesteps | 1209500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00286 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242000 |\n", "| time_elapsed | 6507 |\n", "| total_timesteps | 1210000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0556 |\n", "| value_loss | 0.00287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242100 |\n", "| time_elapsed | 6510 |\n", "| total_timesteps | 1210500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.48 |\n", "| value_loss | 1.42 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242200 |\n", "| time_elapsed | 6512 |\n", "| total_timesteps | 1211000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.19 |\n", "| value_loss | 1.07 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242300 |\n", "| time_elapsed | 6515 |\n", "| total_timesteps | 1211500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00275 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242400 |\n", "| time_elapsed | 6518 |\n", "| total_timesteps | 1212000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.305 |\n", "| value_loss | 0.342 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242500 |\n", "| time_elapsed | 6520 |\n", "| total_timesteps | 1212500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0674 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242600 |\n", "| time_elapsed | 6523 |\n", "| total_timesteps | 1213000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242700 |\n", "| time_elapsed | 6526 |\n", "| total_timesteps | 1213500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0766 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242800 |\n", "| time_elapsed | 6528 |\n", "| total_timesteps | 1214000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0491 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 242900 |\n", "| time_elapsed | 6531 |\n", "| total_timesteps | 1214500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0632 |\n", "| value_loss | 0.00299 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243000 |\n", "| time_elapsed | 6533 |\n", "| total_timesteps | 1215000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0697 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243100 |\n", "| time_elapsed | 6536 |\n", "| total_timesteps | 1215500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0692 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243200 |\n", "| time_elapsed | 6539 |\n", "| total_timesteps | 1216000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00278 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243300 |\n", "| time_elapsed | 6541 |\n", "| total_timesteps | 1216500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.0028 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243400 |\n", "| time_elapsed | 6544 |\n", "| total_timesteps | 1217000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243500 |\n", "| time_elapsed | 6546 |\n", "| total_timesteps | 1217500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0759 |\n", "| value_loss | 0.00297 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243600 |\n", "| time_elapsed | 6549 |\n", "| total_timesteps | 1218000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0549 |\n", "| value_loss | 0.00304 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243700 |\n", "| time_elapsed | 6552 |\n", "| total_timesteps | 1218500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0781 |\n", "| value_loss | 0.00299 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243800 |\n", "| time_elapsed | 6554 |\n", "| total_timesteps | 1219000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0995 |\n", "| value_loss | 0.00289 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 243900 |\n", "| time_elapsed | 6557 |\n", "| total_timesteps | 1219500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00282 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244000 |\n", "| time_elapsed | 6560 |\n", "| total_timesteps | 1220000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244100 |\n", "| time_elapsed | 6562 |\n", "| total_timesteps | 1220500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.313 |\n", "| value_loss | 0.342 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244200 |\n", "| time_elapsed | 6565 |\n", "| total_timesteps | 1221000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0661 |\n", "| value_loss | 0.00295 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244300 |\n", "| time_elapsed | 6567 |\n", "| total_timesteps | 1221500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.932 |\n", "| value_loss | 1.61 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244400 |\n", "| time_elapsed | 6570 |\n", "| total_timesteps | 1222000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0461 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244500 |\n", "| time_elapsed | 6572 |\n", "| total_timesteps | 1222500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.25 |\n", "| value_loss | 1.98 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244600 |\n", "| time_elapsed | 6575 |\n", "| total_timesteps | 1223000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00301 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244700 |\n", "| time_elapsed | 6578 |\n", "| total_timesteps | 1223500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00301 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.8 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244800 |\n", "| time_elapsed | 6580 |\n", "| total_timesteps | 1224000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0674 |\n", "| value_loss | 0.00286 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 244900 |\n", "| time_elapsed | 6583 |\n", "| total_timesteps | 1224500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00294 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 245000 |\n", "| time_elapsed | 6586 |\n", "| total_timesteps | 1225000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.151 |\n", "| value_loss | 0.17 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245100 |\n", "| time_elapsed | 6588 |\n", "| total_timesteps | 1225500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0626 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245200 |\n", "| time_elapsed | 6591 |\n", "| total_timesteps | 1226000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00285 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245300 |\n", "| time_elapsed | 6594 |\n", "| total_timesteps | 1226500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245400 |\n", "| time_elapsed | 6596 |\n", "| total_timesteps | 1227000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0507 |\n", "| value_loss | 0.00293 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245500 |\n", "| time_elapsed | 6599 |\n", "| total_timesteps | 1227500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0539 |\n", "| value_loss | 0.00297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245600 |\n", "| time_elapsed | 6602 |\n", "| total_timesteps | 1228000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0588 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245700 |\n", "| time_elapsed | 6604 |\n", "| total_timesteps | 1228500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0593 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245800 |\n", "| time_elapsed | 6607 |\n", "| total_timesteps | 1229000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0666 |\n", "| value_loss | 0.00291 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 245900 |\n", "| time_elapsed | 6609 |\n", "| total_timesteps | 1229500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00271 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246000 |\n", "| time_elapsed | 6612 |\n", "| total_timesteps | 1230000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.00268 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246100 |\n", "| time_elapsed | 6615 |\n", "| total_timesteps | 1230500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0664 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246200 |\n", "| time_elapsed | 6617 |\n", "| total_timesteps | 1231000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.477 |\n", "| value_loss | 0.517 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246300 |\n", "| time_elapsed | 6620 |\n", "| total_timesteps | 1231500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.052 |\n", "| value_loss | 0.00278 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246400 |\n", "| time_elapsed | 6622 |\n", "| total_timesteps | 1232000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246500 |\n", "| time_elapsed | 6625 |\n", "| total_timesteps | 1232500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0593 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246600 |\n", "| time_elapsed | 6628 |\n", "| total_timesteps | 1233000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00256 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246700 |\n", "| time_elapsed | 6630 |\n", "| total_timesteps | 1233500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.041 |\n", "| value_loss | 0.00251 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246800 |\n", "| time_elapsed | 6633 |\n", "| total_timesteps | 1234000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 246900 |\n", "| time_elapsed | 6635 |\n", "| total_timesteps | 1234500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0582 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247000 |\n", "| time_elapsed | 6638 |\n", "| total_timesteps | 1235000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0749 |\n", "| value_loss | 0.00255 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247100 |\n", "| time_elapsed | 6641 |\n", "| total_timesteps | 1235500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.853 |\n", "| value_loss | 1.25 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247200 |\n", "| time_elapsed | 6643 |\n", "| total_timesteps | 1236000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247300 |\n", "| time_elapsed | 6646 |\n", "| total_timesteps | 1236500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.053 |\n", "| value_loss | 0.00258 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247400 |\n", "| time_elapsed | 6648 |\n", "| total_timesteps | 1237000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0727 |\n", "| value_loss | 0.00256 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247500 |\n", "| time_elapsed | 6651 |\n", "| total_timesteps | 1237500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247600 |\n", "| time_elapsed | 6653 |\n", "| total_timesteps | 1238000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00277 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247700 |\n", "| time_elapsed | 6656 |\n", "| total_timesteps | 1238500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0682 |\n", "| value_loss | 0.00291 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247800 |\n", "| time_elapsed | 6659 |\n", "| total_timesteps | 1239000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00279 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 247900 |\n", "| time_elapsed | 6661 |\n", "| total_timesteps | 1239500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.579 |\n", "| value_loss | 0.342 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248000 |\n", "| time_elapsed | 6664 |\n", "| total_timesteps | 1240000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248100 |\n", "| time_elapsed | 6666 |\n", "| total_timesteps | 1240500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0659 |\n", "| value_loss | 0.00286 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248200 |\n", "| time_elapsed | 6669 |\n", "| total_timesteps | 1241000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248300 |\n", "| time_elapsed | 6671 |\n", "| total_timesteps | 1241500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0512 |\n", "| value_loss | 0.00281 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248400 |\n", "| time_elapsed | 6674 |\n", "| total_timesteps | 1242000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.533 |\n", "| value_loss | 0.341 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248500 |\n", "| time_elapsed | 6677 |\n", "| total_timesteps | 1242500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0908 |\n", "| value_loss | 0.00297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248600 |\n", "| time_elapsed | 6679 |\n", "| total_timesteps | 1243000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0567 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248700 |\n", "| time_elapsed | 6682 |\n", "| total_timesteps | 1243500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00297 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248800 |\n", "| time_elapsed | 6684 |\n", "| total_timesteps | 1244000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0649 |\n", "| value_loss | 0.00307 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 248900 |\n", "| time_elapsed | 6687 |\n", "| total_timesteps | 1244500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0769 |\n", "| value_loss | 0.00303 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249000 |\n", "| time_elapsed | 6690 |\n", "| total_timesteps | 1245000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249100 |\n", "| time_elapsed | 6692 |\n", "| total_timesteps | 1245500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.0028 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249200 |\n", "| time_elapsed | 6695 |\n", "| total_timesteps | 1246000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0483 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249300 |\n", "| time_elapsed | 6697 |\n", "| total_timesteps | 1246500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.47 |\n", "| value_loss | 1.25 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249400 |\n", "| time_elapsed | 6700 |\n", "| total_timesteps | 1247000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0591 |\n", "| value_loss | 0.00269 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249500 |\n", "| time_elapsed | 6703 |\n", "| total_timesteps | 1247500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0521 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249600 |\n", "| time_elapsed | 6705 |\n", "| total_timesteps | 1248000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0671 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249700 |\n", "| time_elapsed | 6708 |\n", "| total_timesteps | 1248500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.065 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249800 |\n", "| time_elapsed | 6710 |\n", "| total_timesteps | 1249000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.03 |\n", "| value_loss | 1.42 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 249900 |\n", "| time_elapsed | 6713 |\n", "| total_timesteps | 1249500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.5 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.86 |\n", "| value_loss | 2.77 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250000 |\n", "| time_elapsed | 6716 |\n", "| total_timesteps | 1250000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00299 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250100 |\n", "| time_elapsed | 6718 |\n", "| total_timesteps | 1250500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00293 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250200 |\n", "| time_elapsed | 6721 |\n", "| total_timesteps | 1251000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00302 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250300 |\n", "| time_elapsed | 6723 |\n", "| total_timesteps | 1251500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.063 |\n", "| value_loss | 0.0029 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250400 |\n", "| time_elapsed | 6726 |\n", "| total_timesteps | 1252000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250500 |\n", "| time_elapsed | 6728 |\n", "| total_timesteps | 1252500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.327 |\n", "| value_loss | 0.341 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250600 |\n", "| time_elapsed | 6731 |\n", "| total_timesteps | 1253000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0596 |\n", "| value_loss | 0.00302 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250700 |\n", "| time_elapsed | 6734 |\n", "| total_timesteps | 1253500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0631 |\n", "| value_loss | 0.00287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250800 |\n", "| time_elapsed | 6736 |\n", "| total_timesteps | 1254000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0455 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 250900 |\n", "| time_elapsed | 6739 |\n", "| total_timesteps | 1254500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00288 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251000 |\n", "| time_elapsed | 6741 |\n", "| total_timesteps | 1255000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0573 |\n", "| value_loss | 0.00271 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251100 |\n", "| time_elapsed | 6744 |\n", "| total_timesteps | 1255500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0798 |\n", "| value_loss | 0.00259 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251200 |\n", "| time_elapsed | 6747 |\n", "| total_timesteps | 1256000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.11 |\n", "| value_loss | 0.694 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251300 |\n", "| time_elapsed | 6749 |\n", "| total_timesteps | 1256500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0876 |\n", "| value_loss | 0.00274 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251400 |\n", "| time_elapsed | 6752 |\n", "| total_timesteps | 1257000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0577 |\n", "| value_loss | 0.00282 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251500 |\n", "| time_elapsed | 6754 |\n", "| total_timesteps | 1257500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.259 |\n", "| value_loss | 0.341 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251600 |\n", "| time_elapsed | 6757 |\n", "| total_timesteps | 1258000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00287 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251700 |\n", "| time_elapsed | 6760 |\n", "| total_timesteps | 1258500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00289 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251800 |\n", "| time_elapsed | 6762 |\n", "| total_timesteps | 1259000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0659 |\n", "| value_loss | 0.00301 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 251900 |\n", "| time_elapsed | 6765 |\n", "| total_timesteps | 1259500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.00289 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252000 |\n", "| time_elapsed | 6767 |\n", "| total_timesteps | 1260000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0628 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252100 |\n", "| time_elapsed | 6770 |\n", "| total_timesteps | 1260500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0815 |\n", "| value_loss | 0.00251 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252200 |\n", "| time_elapsed | 6773 |\n", "| total_timesteps | 1261000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.934 |\n", "| value_loss | 1.25 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252300 |\n", "| time_elapsed | 6775 |\n", "| total_timesteps | 1261500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0731 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252400 |\n", "| time_elapsed | 6778 |\n", "| total_timesteps | 1262000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.358 |\n", "| value_loss | 0.346 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252500 |\n", "| time_elapsed | 6780 |\n", "| total_timesteps | 1262500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252600 |\n", "| time_elapsed | 6783 |\n", "| total_timesteps | 1263000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0656 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252700 |\n", "| time_elapsed | 6785 |\n", "| total_timesteps | 1263500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252800 |\n", "| time_elapsed | 6788 |\n", "| total_timesteps | 1264000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.315 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 252900 |\n", "| time_elapsed | 6790 |\n", "| total_timesteps | 1264500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0765 |\n", "| value_loss | 0.00254 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253000 |\n", "| time_elapsed | 6793 |\n", "| total_timesteps | 1265000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253100 |\n", "| time_elapsed | 6796 |\n", "| total_timesteps | 1265500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.0027 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253200 |\n", "| time_elapsed | 6798 |\n", "| total_timesteps | 1266000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0841 |\n", "| value_loss | 0.00261 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253300 |\n", "| time_elapsed | 6801 |\n", "| total_timesteps | 1266500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0705 |\n", "| value_loss | 0.00272 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253400 |\n", "| time_elapsed | 6803 |\n", "| total_timesteps | 1267000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00283 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253500 |\n", "| time_elapsed | 6806 |\n", "| total_timesteps | 1267500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.044 |\n", "| value_loss | 0.00284 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253600 |\n", "| time_elapsed | 6808 |\n", "| total_timesteps | 1268000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00285 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253700 |\n", "| time_elapsed | 6811 |\n", "| total_timesteps | 1268500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.386 |\n", "| value_loss | 0.516 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253800 |\n", "| time_elapsed | 6814 |\n", "| total_timesteps | 1269000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00266 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 253900 |\n", "| time_elapsed | 6816 |\n", "| total_timesteps | 1269500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0634 |\n", "| value_loss | 0.00264 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254000 |\n", "| time_elapsed | 6819 |\n", "| total_timesteps | 1270000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0363 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254100 |\n", "| time_elapsed | 6821 |\n", "| total_timesteps | 1270500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0576 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 21.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254200 |\n", "| time_elapsed | 6824 |\n", "| total_timesteps | 1271000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254300 |\n", "| time_elapsed | 6826 |\n", "| total_timesteps | 1271500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254400 |\n", "| time_elapsed | 6829 |\n", "| total_timesteps | 1272000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.707 |\n", "| value_loss | 0.523 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254500 |\n", "| time_elapsed | 6831 |\n", "| total_timesteps | 1272500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0444 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254600 |\n", "| time_elapsed | 6834 |\n", "| total_timesteps | 1273000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0554 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254700 |\n", "| time_elapsed | 6837 |\n", "| total_timesteps | 1273500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254800 |\n", "| time_elapsed | 6839 |\n", "| total_timesteps | 1274000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0468 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 21.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 254900 |\n", "| time_elapsed | 6842 |\n", "| total_timesteps | 1274500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0352 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "Eval num_timesteps=1275000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "-------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1275000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.16 |\n", "| value_loss | 2.38 |\n", "-------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 255000 |\n", "| time_elapsed | 6855 |\n", "| total_timesteps | 1275000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 255100 |\n", "| time_elapsed | 6858 |\n", "| total_timesteps | 1275500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0712 |\n", "| value_loss | 0.0025 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 21.2 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 255200 |\n", "| time_elapsed | 6860 |\n", "| total_timesteps | 1276000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.048 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 21 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 255300 |\n", "| time_elapsed | 6863 |\n", "| total_timesteps | 1276500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0456 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.9 |\n", "| time/ | |\n", "| fps | 185 |\n", "| iterations | 255400 |\n", "| time_elapsed | 6865 |\n", "| total_timesteps | 1277000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 255500 |\n", "| time_elapsed | 6868 |\n", "| total_timesteps | 1277500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0469 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 255600 |\n", "| time_elapsed | 6870 |\n", "| total_timesteps | 1278000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 255700 |\n", "| time_elapsed | 6873 |\n", "| total_timesteps | 1278500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0707 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 255800 |\n", "| time_elapsed | 6875 |\n", "| total_timesteps | 1279000 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 255900 |\n", "| time_elapsed | 6878 |\n", "| total_timesteps | 1279500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00182 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256000 |\n", "| time_elapsed | 6880 |\n", "| total_timesteps | 1280000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.00192 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256100 |\n", "| time_elapsed | 6883 |\n", "| total_timesteps | 1280500 |\n", "| train/ | |\n", "| entropy_loss | -1.26 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0376 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256200 |\n", "| time_elapsed | 6886 |\n", "| total_timesteps | 1281000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.365 |\n", "| value_loss | 0.351 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256300 |\n", "| time_elapsed | 6888 |\n", "| total_timesteps | 1281500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0461 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256400 |\n", "| time_elapsed | 6891 |\n", "| total_timesteps | 1282000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.043 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256500 |\n", "| time_elapsed | 6893 |\n", "| total_timesteps | 1282500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0624 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256600 |\n", "| time_elapsed | 6896 |\n", "| total_timesteps | 1283000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0788 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256700 |\n", "| time_elapsed | 6899 |\n", "| total_timesteps | 1283500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0766 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256800 |\n", "| time_elapsed | 6901 |\n", "| total_timesteps | 1284000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0737 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 256900 |\n", "| time_elapsed | 6904 |\n", "| total_timesteps | 1284500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0697 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 542 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257000 |\n", "| time_elapsed | 6906 |\n", "| total_timesteps | 1285000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257100 |\n", "| time_elapsed | 6909 |\n", "| total_timesteps | 1285500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0701 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257200 |\n", "| time_elapsed | 6912 |\n", "| total_timesteps | 1286000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257300 |\n", "| time_elapsed | 6914 |\n", "| total_timesteps | 1286500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257400 |\n", "| time_elapsed | 6917 |\n", "| total_timesteps | 1287000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.724 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257500 |\n", "| time_elapsed | 6919 |\n", "| total_timesteps | 1287500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257600 |\n", "| time_elapsed | 6922 |\n", "| total_timesteps | 1288000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.107 |\n", "| value_loss | 0.174 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257700 |\n", "| time_elapsed | 6924 |\n", "| total_timesteps | 1288500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0377 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257800 |\n", "| time_elapsed | 6927 |\n", "| total_timesteps | 1289000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.801 |\n", "| value_loss | 0.524 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 257900 |\n", "| time_elapsed | 6930 |\n", "| total_timesteps | 1289500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0731 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258000 |\n", "| time_elapsed | 6932 |\n", "| total_timesteps | 1290000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.09 |\n", "| value_loss | 0.701 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258100 |\n", "| time_elapsed | 6935 |\n", "| total_timesteps | 1290500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0772 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258200 |\n", "| time_elapsed | 6937 |\n", "| total_timesteps | 1291000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.063 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258300 |\n", "| time_elapsed | 6940 |\n", "| total_timesteps | 1291500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258400 |\n", "| time_elapsed | 6942 |\n", "| total_timesteps | 1292000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0515 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258500 |\n", "| time_elapsed | 6945 |\n", "| total_timesteps | 1292500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258600 |\n", "| time_elapsed | 6947 |\n", "| total_timesteps | 1293000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0535 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258700 |\n", "| time_elapsed | 6950 |\n", "| total_timesteps | 1293500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.067 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258800 |\n", "| time_elapsed | 6953 |\n", "| total_timesteps | 1294000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0772 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 258900 |\n", "| time_elapsed | 6955 |\n", "| total_timesteps | 1294500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0639 |\n", "| value_loss | 0.00244 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259000 |\n", "| time_elapsed | 6958 |\n", "| total_timesteps | 1295000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259100 |\n", "| time_elapsed | 6960 |\n", "| total_timesteps | 1295500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0627 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259200 |\n", "| time_elapsed | 6963 |\n", "| total_timesteps | 1296000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259300 |\n", "| time_elapsed | 6965 |\n", "| total_timesteps | 1296500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0763 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 549 |\n", "| ep_rew_mean | 20.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259400 |\n", "| time_elapsed | 6968 |\n", "| total_timesteps | 1297000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0415 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259500 |\n", "| time_elapsed | 6970 |\n", "| total_timesteps | 1297500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0515 |\n", "| value_loss | 0.00241 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259600 |\n", "| time_elapsed | 6973 |\n", "| total_timesteps | 1298000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0519 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259700 |\n", "| time_elapsed | 6975 |\n", "| total_timesteps | 1298500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259800 |\n", "| time_elapsed | 6978 |\n", "| total_timesteps | 1299000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 546 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 259900 |\n", "| time_elapsed | 6981 |\n", "| total_timesteps | 1299500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260000 |\n", "| time_elapsed | 6983 |\n", "| total_timesteps | 1300000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260100 |\n", "| time_elapsed | 6986 |\n", "| total_timesteps | 1300500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260200 |\n", "| time_elapsed | 6988 |\n", "| total_timesteps | 1301000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00221 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260300 |\n", "| time_elapsed | 6991 |\n", "| total_timesteps | 1301500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.46 |\n", "| value_loss | 2.56 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260400 |\n", "| time_elapsed | 6993 |\n", "| total_timesteps | 1302000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0305 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260500 |\n", "| time_elapsed | 6996 |\n", "| total_timesteps | 1302500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.249 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 548 |\n", "| ep_rew_mean | 20.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260600 |\n", "| time_elapsed | 6998 |\n", "| total_timesteps | 1303000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 547 |\n", "| ep_rew_mean | 20.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260700 |\n", "| time_elapsed | 7001 |\n", "| total_timesteps | 1303500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260800 |\n", "| time_elapsed | 7004 |\n", "| total_timesteps | 1304000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.47 |\n", "| value_loss | 0.349 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 260900 |\n", "| time_elapsed | 7006 |\n", "| total_timesteps | 1304500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 545 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261000 |\n", "| time_elapsed | 7009 |\n", "| total_timesteps | 1305000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.112 |\n", "| value_loss | 0.175 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 544 |\n", "| ep_rew_mean | 19.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261100 |\n", "| time_elapsed | 7011 |\n", "| total_timesteps | 1305500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.00195 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261200 |\n", "| time_elapsed | 7014 |\n", "| total_timesteps | 1306000 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0381 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 543 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261300 |\n", "| time_elapsed | 7016 |\n", "| total_timesteps | 1306500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.22 |\n", "| value_loss | 0.886 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261400 |\n", "| time_elapsed | 7019 |\n", "| total_timesteps | 1307000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261500 |\n", "| time_elapsed | 7022 |\n", "| total_timesteps | 1307500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261600 |\n", "| time_elapsed | 7024 |\n", "| total_timesteps | 1308000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.949 |\n", "| value_loss | 0.704 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261700 |\n", "| time_elapsed | 7027 |\n", "| total_timesteps | 1308500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.3 |\n", "| value_loss | 0.883 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261800 |\n", "| time_elapsed | 7029 |\n", "| total_timesteps | 1309000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 261900 |\n", "| time_elapsed | 7032 |\n", "| total_timesteps | 1309500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0363 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262000 |\n", "| time_elapsed | 7034 |\n", "| total_timesteps | 1310000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262100 |\n", "| time_elapsed | 7037 |\n", "| total_timesteps | 1310500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.23 |\n", "| value_loss | 0.88 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262200 |\n", "| time_elapsed | 7039 |\n", "| total_timesteps | 1311000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0606 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262300 |\n", "| time_elapsed | 7042 |\n", "| total_timesteps | 1311500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262400 |\n", "| time_elapsed | 7044 |\n", "| total_timesteps | 1312000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.814 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262500 |\n", "| time_elapsed | 7047 |\n", "| total_timesteps | 1312500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0843 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262600 |\n", "| time_elapsed | 7050 |\n", "| total_timesteps | 1313000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262700 |\n", "| time_elapsed | 7052 |\n", "| total_timesteps | 1313500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0435 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262800 |\n", "| time_elapsed | 7055 |\n", "| total_timesteps | 1314000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0416 |\n", "| value_loss | 0.00226 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 262900 |\n", "| time_elapsed | 7057 |\n", "| total_timesteps | 1314500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0323 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263000 |\n", "| time_elapsed | 7060 |\n", "| total_timesteps | 1315000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0443 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263100 |\n", "| time_elapsed | 7062 |\n", "| total_timesteps | 1315500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0476 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263200 |\n", "| time_elapsed | 7065 |\n", "| total_timesteps | 1316000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0337 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263300 |\n", "| time_elapsed | 7068 |\n", "| total_timesteps | 1316500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263400 |\n", "| time_elapsed | 7070 |\n", "| total_timesteps | 1317000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0541 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263500 |\n", "| time_elapsed | 7073 |\n", "| total_timesteps | 1317500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263600 |\n", "| time_elapsed | 7075 |\n", "| total_timesteps | 1318000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0394 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263700 |\n", "| time_elapsed | 7078 |\n", "| total_timesteps | 1318500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.24 |\n", "| value_loss | 0.883 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263800 |\n", "| time_elapsed | 7080 |\n", "| total_timesteps | 1319000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0548 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 263900 |\n", "| time_elapsed | 7083 |\n", "| total_timesteps | 1319500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0669 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264000 |\n", "| time_elapsed | 7085 |\n", "| total_timesteps | 1320000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.669 |\n", "| value_loss | 0.35 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264100 |\n", "| time_elapsed | 7088 |\n", "| total_timesteps | 1320500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0547 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264200 |\n", "| time_elapsed | 7090 |\n", "| total_timesteps | 1321000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264300 |\n", "| time_elapsed | 7093 |\n", "| total_timesteps | 1321500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0614 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264400 |\n", "| time_elapsed | 7096 |\n", "| total_timesteps | 1322000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0534 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264500 |\n", "| time_elapsed | 7098 |\n", "| total_timesteps | 1322500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0495 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264600 |\n", "| time_elapsed | 7101 |\n", "| total_timesteps | 1323000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.00256 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264700 |\n", "| time_elapsed | 7103 |\n", "| total_timesteps | 1323500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0404 |\n", "| value_loss | 0.00248 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264800 |\n", "| time_elapsed | 7106 |\n", "| total_timesteps | 1324000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0411 |\n", "| value_loss | 0.00248 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 264900 |\n", "| time_elapsed | 7109 |\n", "| total_timesteps | 1324500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0396 |\n", "| value_loss | 0.00247 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265000 |\n", "| time_elapsed | 7111 |\n", "| total_timesteps | 1325000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0718 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265100 |\n", "| time_elapsed | 7114 |\n", "| total_timesteps | 1325500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0595 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265200 |\n", "| time_elapsed | 7116 |\n", "| total_timesteps | 1326000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265300 |\n", "| time_elapsed | 7119 |\n", "| total_timesteps | 1326500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.05 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265400 |\n", "| time_elapsed | 7121 |\n", "| total_timesteps | 1327000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0708 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265500 |\n", "| time_elapsed | 7124 |\n", "| total_timesteps | 1327500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.528 |\n", "| value_loss | 0.349 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265600 |\n", "| time_elapsed | 7127 |\n", "| total_timesteps | 1328000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.372 |\n", "| value_loss | 0.528 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265700 |\n", "| time_elapsed | 7129 |\n", "| total_timesteps | 1328500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265800 |\n", "| time_elapsed | 7132 |\n", "| total_timesteps | 1329000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.2 |\n", "| value_loss | 2.01 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 265900 |\n", "| time_elapsed | 7134 |\n", "| total_timesteps | 1329500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266000 |\n", "| time_elapsed | 7137 |\n", "| total_timesteps | 1330000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0369 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266100 |\n", "| time_elapsed | 7139 |\n", "| total_timesteps | 1330500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0347 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266200 |\n", "| time_elapsed | 7142 |\n", "| total_timesteps | 1331000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0257 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266300 |\n", "| time_elapsed | 7145 |\n", "| total_timesteps | 1331500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0823 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266400 |\n", "| time_elapsed | 7147 |\n", "| total_timesteps | 1332000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0474 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266500 |\n", "| time_elapsed | 7150 |\n", "| total_timesteps | 1332500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0334 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266600 |\n", "| time_elapsed | 7152 |\n", "| total_timesteps | 1333000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0282 |\n", "| value_loss | 0.00197 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266700 |\n", "| time_elapsed | 7155 |\n", "| total_timesteps | 1333500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0303 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266800 |\n", "| time_elapsed | 7158 |\n", "| total_timesteps | 1334000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 266900 |\n", "| time_elapsed | 7160 |\n", "| total_timesteps | 1334500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267000 |\n", "| time_elapsed | 7163 |\n", "| total_timesteps | 1335000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0718 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267100 |\n", "| time_elapsed | 7165 |\n", "| total_timesteps | 1335500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.747 |\n", "| value_loss | 0.527 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267200 |\n", "| time_elapsed | 7168 |\n", "| total_timesteps | 1336000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0432 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267300 |\n", "| time_elapsed | 7170 |\n", "| total_timesteps | 1336500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0531 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267400 |\n", "| time_elapsed | 7173 |\n", "| total_timesteps | 1337000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0537 |\n", "| value_loss | 0.00196 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267500 |\n", "| time_elapsed | 7175 |\n", "| total_timesteps | 1337500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0261 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267600 |\n", "| time_elapsed | 7178 |\n", "| total_timesteps | 1338000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.06 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267700 |\n", "| time_elapsed | 7180 |\n", "| total_timesteps | 1338500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0475 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267800 |\n", "| time_elapsed | 7183 |\n", "| total_timesteps | 1339000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0356 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 267900 |\n", "| time_elapsed | 7186 |\n", "| total_timesteps | 1339500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0263 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268000 |\n", "| time_elapsed | 7188 |\n", "| total_timesteps | 1340000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0472 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268100 |\n", "| time_elapsed | 7191 |\n", "| total_timesteps | 1340500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00201 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268200 |\n", "| time_elapsed | 7194 |\n", "| total_timesteps | 1341000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0543 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268300 |\n", "| time_elapsed | 7196 |\n", "| total_timesteps | 1341500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0356 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268400 |\n", "| time_elapsed | 7199 |\n", "| total_timesteps | 1342000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0664 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268500 |\n", "| time_elapsed | 7201 |\n", "| total_timesteps | 1342500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.245 |\n", "| value_loss | 0.176 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268600 |\n", "| time_elapsed | 7204 |\n", "| total_timesteps | 1343000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268700 |\n", "| time_elapsed | 7207 |\n", "| total_timesteps | 1343500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0479 |\n", "| value_loss | 0.00177 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268800 |\n", "| time_elapsed | 7209 |\n", "| total_timesteps | 1344000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0387 |\n", "| value_loss | 0.00184 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 268900 |\n", "| time_elapsed | 7212 |\n", "| total_timesteps | 1344500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.802 |\n", "| value_loss | 0.707 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269000 |\n", "| time_elapsed | 7214 |\n", "| total_timesteps | 1345000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0628 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269100 |\n", "| time_elapsed | 7217 |\n", "| total_timesteps | 1345500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269200 |\n", "| time_elapsed | 7219 |\n", "| total_timesteps | 1346000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0538 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269300 |\n", "| time_elapsed | 7222 |\n", "| total_timesteps | 1346500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.617 |\n", "| value_loss | 0.351 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269400 |\n", "| time_elapsed | 7224 |\n", "| total_timesteps | 1347000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.957 |\n", "| value_loss | 0.707 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269500 |\n", "| time_elapsed | 7227 |\n", "| total_timesteps | 1347500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0445 |\n", "| value_loss | 0.00185 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269600 |\n", "| time_elapsed | 7230 |\n", "| total_timesteps | 1348000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269700 |\n", "| time_elapsed | 7232 |\n", "| total_timesteps | 1348500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00176 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269800 |\n", "| time_elapsed | 7235 |\n", "| total_timesteps | 1349000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0373 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 269900 |\n", "| time_elapsed | 7237 |\n", "| total_timesteps | 1349500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00181 |\n", "------------------------------------\n", "Eval num_timesteps=1350000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1350000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0497 |\n", "| value_loss | 0.00173 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270000 |\n", "| time_elapsed | 7250 |\n", "| total_timesteps | 1350000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270100 |\n", "| time_elapsed | 7253 |\n", "| total_timesteps | 1350500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00178 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 524 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270200 |\n", "| time_elapsed | 7255 |\n", "| total_timesteps | 1351000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0348 |\n", "| value_loss | 0.0017 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270300 |\n", "| time_elapsed | 7258 |\n", "| total_timesteps | 1351500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 525 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270400 |\n", "| time_elapsed | 7261 |\n", "| total_timesteps | 1352000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0513 |\n", "| value_loss | 0.00184 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270500 |\n", "| time_elapsed | 7263 |\n", "| total_timesteps | 1352500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00183 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270600 |\n", "| time_elapsed | 7266 |\n", "| total_timesteps | 1353000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0652 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270700 |\n", "| time_elapsed | 7268 |\n", "| total_timesteps | 1353500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0609 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270800 |\n", "| time_elapsed | 7271 |\n", "| total_timesteps | 1354000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 270900 |\n", "| time_elapsed | 7273 |\n", "| total_timesteps | 1354500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0641 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271000 |\n", "| time_elapsed | 7276 |\n", "| total_timesteps | 1355000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0532 |\n", "| value_loss | 0.00202 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271100 |\n", "| time_elapsed | 7278 |\n", "| total_timesteps | 1355500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0457 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271200 |\n", "| time_elapsed | 7281 |\n", "| total_timesteps | 1356000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271300 |\n", "| time_elapsed | 7284 |\n", "| total_timesteps | 1356500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.912 |\n", "| value_loss | 0.883 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271400 |\n", "| time_elapsed | 7286 |\n", "| total_timesteps | 1357000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0547 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 527 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271500 |\n", "| time_elapsed | 7289 |\n", "| total_timesteps | 1357500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0709 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271600 |\n", "| time_elapsed | 7291 |\n", "| total_timesteps | 1358000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0592 |\n", "| value_loss | 0.00191 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 526 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271700 |\n", "| time_elapsed | 7294 |\n", "| total_timesteps | 1358500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0386 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 528 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271800 |\n", "| time_elapsed | 7297 |\n", "| total_timesteps | 1359000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0539 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 271900 |\n", "| time_elapsed | 7299 |\n", "| total_timesteps | 1359500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0483 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272000 |\n", "| time_elapsed | 7302 |\n", "| total_timesteps | 1360000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0406 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272100 |\n", "| time_elapsed | 7304 |\n", "| total_timesteps | 1360500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0471 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272200 |\n", "| time_elapsed | 7307 |\n", "| total_timesteps | 1361000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.825 |\n", "| value_loss | 1.26 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272300 |\n", "| time_elapsed | 7309 |\n", "| total_timesteps | 1361500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.626 |\n", "| value_loss | 0.527 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272400 |\n", "| time_elapsed | 7312 |\n", "| total_timesteps | 1362000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0545 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272500 |\n", "| time_elapsed | 7315 |\n", "| total_timesteps | 1362500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0368 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272600 |\n", "| time_elapsed | 7317 |\n", "| total_timesteps | 1363000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0422 |\n", "| value_loss | 0.00196 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272700 |\n", "| time_elapsed | 7320 |\n", "| total_timesteps | 1363500 |\n", "| train/ | |\n", "| entropy_loss | -1.25 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0429 |\n", "| value_loss | 0.00187 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272800 |\n", "| time_elapsed | 7322 |\n", "| total_timesteps | 1364000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0438 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 272900 |\n", "| time_elapsed | 7325 |\n", "| total_timesteps | 1364500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0473 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273000 |\n", "| time_elapsed | 7327 |\n", "| total_timesteps | 1365000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0721 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273100 |\n", "| time_elapsed | 7330 |\n", "| total_timesteps | 1365500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.566 |\n", "| value_loss | 0.348 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273200 |\n", "| time_elapsed | 7333 |\n", "| total_timesteps | 1366000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0359 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273300 |\n", "| time_elapsed | 7335 |\n", "| total_timesteps | 1366500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 2.98e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.213 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273400 |\n", "| time_elapsed | 7338 |\n", "| total_timesteps | 1367000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0423 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273500 |\n", "| time_elapsed | 7340 |\n", "| total_timesteps | 1367500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273600 |\n", "| time_elapsed | 7343 |\n", "| total_timesteps | 1368000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0417 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273700 |\n", "| time_elapsed | 7346 |\n", "| total_timesteps | 1368500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0608 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273800 |\n", "| time_elapsed | 7348 |\n", "| total_timesteps | 1369000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0546 |\n", "| value_loss | 0.00225 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 273900 |\n", "| time_elapsed | 7351 |\n", "| total_timesteps | 1369500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.39 |\n", "| value_loss | 1.99 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274000 |\n", "| time_elapsed | 7353 |\n", "| total_timesteps | 1370000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0402 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274100 |\n", "| time_elapsed | 7356 |\n", "| total_timesteps | 1370500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0715 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274200 |\n", "| time_elapsed | 7358 |\n", "| total_timesteps | 1371000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274300 |\n", "| time_elapsed | 7361 |\n", "| total_timesteps | 1371500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0559 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274400 |\n", "| time_elapsed | 7363 |\n", "| total_timesteps | 1372000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0337 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274500 |\n", "| time_elapsed | 7366 |\n", "| total_timesteps | 1372500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0596 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274600 |\n", "| time_elapsed | 7368 |\n", "| total_timesteps | 1373000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0661 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274700 |\n", "| time_elapsed | 7371 |\n", "| total_timesteps | 1373500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.43 |\n", "| value_loss | 0.882 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274800 |\n", "| time_elapsed | 7374 |\n", "| total_timesteps | 1374000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.061 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 274900 |\n", "| time_elapsed | 7376 |\n", "| total_timesteps | 1374500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275000 |\n", "| time_elapsed | 7379 |\n", "| total_timesteps | 1375000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.059 |\n", "| value_loss | 0.0018 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275100 |\n", "| time_elapsed | 7381 |\n", "| total_timesteps | 1375500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0425 |\n", "| value_loss | 0.00189 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275200 |\n", "| time_elapsed | 7384 |\n", "| total_timesteps | 1376000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0596 |\n", "| value_loss | 0.00186 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 17.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275300 |\n", "| time_elapsed | 7387 |\n", "| total_timesteps | 1376500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275400 |\n", "| time_elapsed | 7389 |\n", "| total_timesteps | 1377000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0454 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275500 |\n", "| time_elapsed | 7392 |\n", "| total_timesteps | 1377500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0511 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275600 |\n", "| time_elapsed | 7394 |\n", "| total_timesteps | 1378000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0656 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 17.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275700 |\n", "| time_elapsed | 7397 |\n", "| total_timesteps | 1378500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00188 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275800 |\n", "| time_elapsed | 7400 |\n", "| total_timesteps | 1379000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0618 |\n", "| value_loss | 0.00191 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 275900 |\n", "| time_elapsed | 7402 |\n", "| total_timesteps | 1379500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0408 |\n", "| value_loss | 0.00199 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276000 |\n", "| time_elapsed | 7405 |\n", "| total_timesteps | 1380000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0345 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 17.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276100 |\n", "| time_elapsed | 7407 |\n", "| total_timesteps | 1380500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0549 |\n", "| value_loss | 0.00215 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276200 |\n", "| time_elapsed | 7410 |\n", "| total_timesteps | 1381000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0722 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276300 |\n", "| time_elapsed | 7412 |\n", "| total_timesteps | 1381500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0395 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276400 |\n", "| time_elapsed | 7415 |\n", "| total_timesteps | 1382000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0399 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276500 |\n", "| time_elapsed | 7418 |\n", "| total_timesteps | 1382500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0343 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276600 |\n", "| time_elapsed | 7420 |\n", "| total_timesteps | 1383000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0366 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276700 |\n", "| time_elapsed | 7423 |\n", "| total_timesteps | 1383500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.047 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276800 |\n", "| time_elapsed | 7425 |\n", "| total_timesteps | 1384000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0557 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 276900 |\n", "| time_elapsed | 7428 |\n", "| total_timesteps | 1384500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.03 |\n", "| value_loss | 1.82 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277000 |\n", "| time_elapsed | 7430 |\n", "| total_timesteps | 1385000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0286 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277100 |\n", "| time_elapsed | 7433 |\n", "| total_timesteps | 1385500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0449 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277200 |\n", "| time_elapsed | 7436 |\n", "| total_timesteps | 1386000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277300 |\n", "| time_elapsed | 7438 |\n", "| total_timesteps | 1386500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.217 |\n", "| value_loss | 0.372 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277400 |\n", "| time_elapsed | 7441 |\n", "| total_timesteps | 1387000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0543 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277500 |\n", "| time_elapsed | 7443 |\n", "| total_timesteps | 1387500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.759 |\n", "| value_loss | 0.7 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277600 |\n", "| time_elapsed | 7446 |\n", "| total_timesteps | 1388000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277700 |\n", "| time_elapsed | 7448 |\n", "| total_timesteps | 1388500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0295 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277800 |\n", "| time_elapsed | 7451 |\n", "| total_timesteps | 1389000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.105 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 277900 |\n", "| time_elapsed | 7453 |\n", "| total_timesteps | 1389500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0368 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278000 |\n", "| time_elapsed | 7456 |\n", "| total_timesteps | 1390000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0609 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278100 |\n", "| time_elapsed | 7459 |\n", "| total_timesteps | 1390500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0777 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278200 |\n", "| time_elapsed | 7461 |\n", "| total_timesteps | 1391000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278300 |\n", "| time_elapsed | 7464 |\n", "| total_timesteps | 1391500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0684 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278400 |\n", "| time_elapsed | 7466 |\n", "| total_timesteps | 1392000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0707 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278500 |\n", "| time_elapsed | 7469 |\n", "| total_timesteps | 1392500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278600 |\n", "| time_elapsed | 7471 |\n", "| total_timesteps | 1393000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.51 |\n", "| value_loss | 2.38 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278700 |\n", "| time_elapsed | 7474 |\n", "| total_timesteps | 1393500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278800 |\n", "| time_elapsed | 7477 |\n", "| total_timesteps | 1394000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.058 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 278900 |\n", "| time_elapsed | 7479 |\n", "| total_timesteps | 1394500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279000 |\n", "| time_elapsed | 7482 |\n", "| total_timesteps | 1395000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0418 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279100 |\n", "| time_elapsed | 7484 |\n", "| total_timesteps | 1395500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0442 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279200 |\n", "| time_elapsed | 7487 |\n", "| total_timesteps | 1396000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0385 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279300 |\n", "| time_elapsed | 7490 |\n", "| total_timesteps | 1396500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0553 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279400 |\n", "| time_elapsed | 7492 |\n", "| total_timesteps | 1397000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0652 |\n", "| value_loss | 0.00209 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279500 |\n", "| time_elapsed | 7495 |\n", "| total_timesteps | 1397500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0607 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279600 |\n", "| time_elapsed | 7497 |\n", "| total_timesteps | 1398000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0594 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279700 |\n", "| time_elapsed | 7500 |\n", "| total_timesteps | 1398500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0663 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279800 |\n", "| time_elapsed | 7502 |\n", "| total_timesteps | 1399000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.061 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 279900 |\n", "| time_elapsed | 7505 |\n", "| total_timesteps | 1399500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280000 |\n", "| time_elapsed | 7508 |\n", "| total_timesteps | 1400000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.056 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280100 |\n", "| time_elapsed | 7510 |\n", "| total_timesteps | 1400500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280200 |\n", "| time_elapsed | 7513 |\n", "| total_timesteps | 1401000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.7 |\n", "| value_loss | 0.524 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280300 |\n", "| time_elapsed | 7515 |\n", "| total_timesteps | 1401500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280400 |\n", "| time_elapsed | 7518 |\n", "| total_timesteps | 1402000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280500 |\n", "| time_elapsed | 7520 |\n", "| total_timesteps | 1402500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0631 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280600 |\n", "| time_elapsed | 7523 |\n", "| total_timesteps | 1403000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280700 |\n", "| time_elapsed | 7526 |\n", "| total_timesteps | 1403500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280800 |\n", "| time_elapsed | 7528 |\n", "| total_timesteps | 1404000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0648 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 280900 |\n", "| time_elapsed | 7531 |\n", "| total_timesteps | 1404500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0482 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281000 |\n", "| time_elapsed | 7533 |\n", "| total_timesteps | 1405000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0591 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281100 |\n", "| time_elapsed | 7536 |\n", "| total_timesteps | 1405500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0525 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281200 |\n", "| time_elapsed | 7538 |\n", "| total_timesteps | 1406000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0685 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281300 |\n", "| time_elapsed | 7541 |\n", "| total_timesteps | 1406500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0699 |\n", "| value_loss | 0.00237 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281400 |\n", "| time_elapsed | 7543 |\n", "| total_timesteps | 1407000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0779 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281500 |\n", "| time_elapsed | 7546 |\n", "| total_timesteps | 1407500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.545 |\n", "| value_loss | 0.347 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281600 |\n", "| time_elapsed | 7548 |\n", "| total_timesteps | 1408000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0369 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281700 |\n", "| time_elapsed | 7551 |\n", "| total_timesteps | 1408500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.115 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281800 |\n", "| time_elapsed | 7554 |\n", "| total_timesteps | 1409000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0563 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 281900 |\n", "| time_elapsed | 7556 |\n", "| total_timesteps | 1409500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.063 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282000 |\n", "| time_elapsed | 7559 |\n", "| total_timesteps | 1410000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0324 |\n", "| value_loss | 0.00185 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282100 |\n", "| time_elapsed | 7561 |\n", "| total_timesteps | 1410500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0494 |\n", "| value_loss | 0.00199 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282200 |\n", "| time_elapsed | 7564 |\n", "| total_timesteps | 1411000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0441 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282300 |\n", "| time_elapsed | 7566 |\n", "| total_timesteps | 1411500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0658 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282400 |\n", "| time_elapsed | 7569 |\n", "| total_timesteps | 1412000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282500 |\n", "| time_elapsed | 7571 |\n", "| total_timesteps | 1412500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0364 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282600 |\n", "| time_elapsed | 7574 |\n", "| total_timesteps | 1413000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.792 |\n", "| value_loss | 0.88 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282700 |\n", "| time_elapsed | 7577 |\n", "| total_timesteps | 1413500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0318 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282800 |\n", "| time_elapsed | 7579 |\n", "| total_timesteps | 1414000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0721 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 282900 |\n", "| time_elapsed | 7582 |\n", "| total_timesteps | 1414500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0341 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283000 |\n", "| time_elapsed | 7584 |\n", "| total_timesteps | 1415000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283100 |\n", "| time_elapsed | 7587 |\n", "| total_timesteps | 1415500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.32 |\n", "| value_loss | 1.09 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283200 |\n", "| time_elapsed | 7589 |\n", "| total_timesteps | 1416000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0436 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283300 |\n", "| time_elapsed | 7592 |\n", "| total_timesteps | 1416500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0781 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283400 |\n", "| time_elapsed | 7595 |\n", "| total_timesteps | 1417000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0629 |\n", "| value_loss | 0.00252 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283500 |\n", "| time_elapsed | 7597 |\n", "| total_timesteps | 1417500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0749 |\n", "| value_loss | 0.173 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283600 |\n", "| time_elapsed | 7600 |\n", "| total_timesteps | 1418000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.07 |\n", "| value_loss | 3.67 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283700 |\n", "| time_elapsed | 7602 |\n", "| total_timesteps | 1418500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0381 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283800 |\n", "| time_elapsed | 7605 |\n", "| total_timesteps | 1419000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0686 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 283900 |\n", "| time_elapsed | 7607 |\n", "| total_timesteps | 1419500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.874 |\n", "| value_loss | 0.702 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284000 |\n", "| time_elapsed | 7610 |\n", "| total_timesteps | 1420000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284100 |\n", "| time_elapsed | 7612 |\n", "| total_timesteps | 1420500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284200 |\n", "| time_elapsed | 7615 |\n", "| total_timesteps | 1421000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0544 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284300 |\n", "| time_elapsed | 7618 |\n", "| total_timesteps | 1421500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0683 |\n", "| value_loss | 0.00216 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284400 |\n", "| time_elapsed | 7620 |\n", "| total_timesteps | 1422000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284500 |\n", "| time_elapsed | 7623 |\n", "| total_timesteps | 1422500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0431 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284600 |\n", "| time_elapsed | 7625 |\n", "| total_timesteps | 1423000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0593 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284700 |\n", "| time_elapsed | 7628 |\n", "| total_timesteps | 1423500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0527 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284800 |\n", "| time_elapsed | 7631 |\n", "| total_timesteps | 1424000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0679 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 284900 |\n", "| time_elapsed | 7633 |\n", "| total_timesteps | 1424500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0575 |\n", "| value_loss | 0.00239 |\n", "------------------------------------\n", "Eval num_timesteps=1425000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1425000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0584 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285000 |\n", "| time_elapsed | 7646 |\n", "| total_timesteps | 1425000 |\n", "---------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285100 |\n", "| time_elapsed | 7649 |\n", "| total_timesteps | 1425500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0447 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285200 |\n", "| time_elapsed | 7652 |\n", "| total_timesteps | 1426000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0802 |\n", "| value_loss | 0.00226 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285300 |\n", "| time_elapsed | 7654 |\n", "| total_timesteps | 1426500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0401 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285400 |\n", "| time_elapsed | 7657 |\n", "| total_timesteps | 1427000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285500 |\n", "| time_elapsed | 7659 |\n", "| total_timesteps | 1427500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285600 |\n", "| time_elapsed | 7662 |\n", "| total_timesteps | 1428000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0484 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285700 |\n", "| time_elapsed | 7664 |\n", "| total_timesteps | 1428500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0605 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285800 |\n", "| time_elapsed | 7667 |\n", "| total_timesteps | 1429000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0578 |\n", "| value_loss | 0.00204 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 285900 |\n", "| time_elapsed | 7669 |\n", "| total_timesteps | 1429500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0555 |\n", "| value_loss | 0.00212 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286000 |\n", "| time_elapsed | 7672 |\n", "| total_timesteps | 1430000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.47 |\n", "| value_loss | 1.44 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286100 |\n", "| time_elapsed | 7675 |\n", "| total_timesteps | 1430500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0604 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286200 |\n", "| time_elapsed | 7677 |\n", "| total_timesteps | 1431000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0788 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286300 |\n", "| time_elapsed | 7680 |\n", "| total_timesteps | 1431500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0434 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286400 |\n", "| time_elapsed | 7682 |\n", "| total_timesteps | 1432000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.46 |\n", "| value_loss | 1.99 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286500 |\n", "| time_elapsed | 7685 |\n", "| total_timesteps | 1432500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.49 |\n", "| value_loss | 0.52 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286600 |\n", "| time_elapsed | 7687 |\n", "| total_timesteps | 1433000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00232 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286700 |\n", "| time_elapsed | 7690 |\n", "| total_timesteps | 1433500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0466 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286800 |\n", "| time_elapsed | 7692 |\n", "| total_timesteps | 1434000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.729 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 286900 |\n", "| time_elapsed | 7695 |\n", "| total_timesteps | 1434500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.48 |\n", "| value_loss | 2.56 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287000 |\n", "| time_elapsed | 7698 |\n", "| total_timesteps | 1435000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0397 |\n", "| value_loss | 0.0019 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287100 |\n", "| time_elapsed | 7700 |\n", "| total_timesteps | 1435500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.404 |\n", "| value_loss | 0.176 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287200 |\n", "| time_elapsed | 7703 |\n", "| total_timesteps | 1436000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0585 |\n", "| value_loss | 0.00195 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287300 |\n", "| time_elapsed | 7705 |\n", "| total_timesteps | 1436500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0488 |\n", "| value_loss | 0.00197 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287400 |\n", "| time_elapsed | 7708 |\n", "| total_timesteps | 1437000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0863 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287500 |\n", "| time_elapsed | 7710 |\n", "| total_timesteps | 1437500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0702 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287600 |\n", "| time_elapsed | 7713 |\n", "| total_timesteps | 1438000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0421 |\n", "| value_loss | 0.00209 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287700 |\n", "| time_elapsed | 7716 |\n", "| total_timesteps | 1438500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0569 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287800 |\n", "| time_elapsed | 7718 |\n", "| total_timesteps | 1439000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0896 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 287900 |\n", "| time_elapsed | 7721 |\n", "| total_timesteps | 1439500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0617 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288000 |\n", "| time_elapsed | 7723 |\n", "| total_timesteps | 1440000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0564 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288100 |\n", "| time_elapsed | 7726 |\n", "| total_timesteps | 1440500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 1.79e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0522 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288200 |\n", "| time_elapsed | 7728 |\n", "| total_timesteps | 1441000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0449 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288300 |\n", "| time_elapsed | 7731 |\n", "| total_timesteps | 1441500 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0622 |\n", "| value_loss | 0.00222 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288400 |\n", "| time_elapsed | 7734 |\n", "| total_timesteps | 1442000 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00214 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288500 |\n", "| time_elapsed | 7736 |\n", "| total_timesteps | 1442500 |\n", "| train/ | |\n", "| entropy_loss | -1.24 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0516 |\n", "| value_loss | 0.00206 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288600 |\n", "| time_elapsed | 7739 |\n", "| total_timesteps | 1443000 |\n", "| train/ | |\n", "| entropy_loss | -1.23 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.55 |\n", "| value_loss | 2.56 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288700 |\n", "| time_elapsed | 7741 |\n", "| total_timesteps | 1443500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0543 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288800 |\n", "| time_elapsed | 7744 |\n", "| total_timesteps | 1444000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0514 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 288900 |\n", "| time_elapsed | 7746 |\n", "| total_timesteps | 1444500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.84 |\n", "| value_loss | 0.702 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289000 |\n", "| time_elapsed | 7749 |\n", "| total_timesteps | 1445000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0679 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289100 |\n", "| time_elapsed | 7751 |\n", "| total_timesteps | 1445500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0654 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289200 |\n", "| time_elapsed | 7754 |\n", "| total_timesteps | 1446000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0603 |\n", "| value_loss | 0.00203 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289300 |\n", "| time_elapsed | 7757 |\n", "| total_timesteps | 1446500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289400 |\n", "| time_elapsed | 7759 |\n", "| total_timesteps | 1447000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.033 |\n", "| value_loss | 0.00198 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289500 |\n", "| time_elapsed | 7762 |\n", "| total_timesteps | 1447500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.21 |\n", "| value_loss | 2.56 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289600 |\n", "| time_elapsed | 7764 |\n", "| total_timesteps | 1448000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0435 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289700 |\n", "| time_elapsed | 7767 |\n", "| total_timesteps | 1448500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0665 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289800 |\n", "| time_elapsed | 7770 |\n", "| total_timesteps | 1449000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.492 |\n", "| value_loss | 0.525 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 289900 |\n", "| time_elapsed | 7772 |\n", "| total_timesteps | 1449500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290000 |\n", "| time_elapsed | 7775 |\n", "| total_timesteps | 1450000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0419 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290100 |\n", "| time_elapsed | 7777 |\n", "| total_timesteps | 1450500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0776 |\n", "| value_loss | 0.002 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290200 |\n", "| time_elapsed | 7780 |\n", "| total_timesteps | 1451000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0583 |\n", "| value_loss | 0.00194 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290300 |\n", "| time_elapsed | 7782 |\n", "| total_timesteps | 1451500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0674 |\n", "| value_loss | 0.00208 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290400 |\n", "| time_elapsed | 7785 |\n", "| total_timesteps | 1452000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0449 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290500 |\n", "| time_elapsed | 7787 |\n", "| total_timesteps | 1452500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0437 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290600 |\n", "| time_elapsed | 7790 |\n", "| total_timesteps | 1453000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0492 |\n", "| value_loss | 0.00217 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290700 |\n", "| time_elapsed | 7793 |\n", "| total_timesteps | 1453500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.039 |\n", "| value_loss | 0.00214 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290800 |\n", "| time_elapsed | 7795 |\n", "| total_timesteps | 1454000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0569 |\n", "| value_loss | 0.00208 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 290900 |\n", "| time_elapsed | 7798 |\n", "| total_timesteps | 1454500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0611 |\n", "| value_loss | 0.00219 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291000 |\n", "| time_elapsed | 7800 |\n", "| total_timesteps | 1455000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0552 |\n", "| value_loss | 0.00225 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291100 |\n", "| time_elapsed | 7803 |\n", "| total_timesteps | 1455500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.051 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291200 |\n", "| time_elapsed | 7806 |\n", "| total_timesteps | 1456000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0501 |\n", "| value_loss | 0.00218 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291300 |\n", "| time_elapsed | 7808 |\n", "| total_timesteps | 1456500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.189 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291400 |\n", "| time_elapsed | 7811 |\n", "| total_timesteps | 1457000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0567 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291500 |\n", "| time_elapsed | 7813 |\n", "| total_timesteps | 1457500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0392 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291600 |\n", "| time_elapsed | 7816 |\n", "| total_timesteps | 1458000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0487 |\n", "| value_loss | 0.00212 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291700 |\n", "| time_elapsed | 7818 |\n", "| total_timesteps | 1458500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0639 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291800 |\n", "| time_elapsed | 7821 |\n", "| total_timesteps | 1459000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0354 |\n", "| value_loss | 0.00209 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 291900 |\n", "| time_elapsed | 7824 |\n", "| total_timesteps | 1459500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0348 |\n", "| value_loss | 0.00229 |\n", "-------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292000 |\n", "| time_elapsed | 7826 |\n", "| total_timesteps | 1460000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0463 |\n", "| value_loss | 0.00223 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292100 |\n", "| time_elapsed | 7829 |\n", "| total_timesteps | 1460500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0294 |\n", "| value_loss | 0.00201 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292200 |\n", "| time_elapsed | 7832 |\n", "| total_timesteps | 1461000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0407 |\n", "| value_loss | 0.00223 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292300 |\n", "| time_elapsed | 7834 |\n", "| total_timesteps | 1461500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00218 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292400 |\n", "| time_elapsed | 7837 |\n", "| total_timesteps | 1462000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.62 |\n", "| value_loss | 0.346 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292500 |\n", "| time_elapsed | 7839 |\n", "| total_timesteps | 1462500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0326 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292600 |\n", "| time_elapsed | 7842 |\n", "| total_timesteps | 1463000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.585 |\n", "| value_loss | 0.523 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292700 |\n", "| time_elapsed | 7844 |\n", "| total_timesteps | 1463500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0659 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292800 |\n", "| time_elapsed | 7847 |\n", "| total_timesteps | 1464000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.04 |\n", "| value_loss | 1.99 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 292900 |\n", "| time_elapsed | 7850 |\n", "| total_timesteps | 1464500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.41 |\n", "| value_loss | 2.55 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293000 |\n", "| time_elapsed | 7852 |\n", "| total_timesteps | 1465000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00215 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293100 |\n", "| time_elapsed | 7855 |\n", "| total_timesteps | 1465500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0566 |\n", "| value_loss | 0.00228 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293200 |\n", "| time_elapsed | 7857 |\n", "| total_timesteps | 1466000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -1.07 |\n", "| value_loss | 1.29 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293300 |\n", "| time_elapsed | 7860 |\n", "| total_timesteps | 1466500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.066 |\n", "| value_loss | 0.00216 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293400 |\n", "| time_elapsed | 7862 |\n", "| total_timesteps | 1467000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0413 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293500 |\n", "| time_elapsed | 7865 |\n", "| total_timesteps | 1467500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.036 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293600 |\n", "| time_elapsed | 7868 |\n", "| total_timesteps | 1468000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0307 |\n", "| value_loss | 0.00234 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293700 |\n", "| time_elapsed | 7870 |\n", "| total_timesteps | 1468500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0433 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293800 |\n", "| time_elapsed | 7873 |\n", "| total_timesteps | 1469000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0448 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 293900 |\n", "| time_elapsed | 7875 |\n", "| total_timesteps | 1469500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.048 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294000 |\n", "| time_elapsed | 7878 |\n", "| total_timesteps | 1470000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0485 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294100 |\n", "| time_elapsed | 7880 |\n", "| total_timesteps | 1470500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0305 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294200 |\n", "| time_elapsed | 7883 |\n", "| total_timesteps | 1471000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 529 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294300 |\n", "| time_elapsed | 7885 |\n", "| total_timesteps | 1471500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.86 |\n", "| value_loss | 1.99 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294400 |\n", "| time_elapsed | 7888 |\n", "| total_timesteps | 1472000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0571 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 530 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294500 |\n", "| time_elapsed | 7890 |\n", "| total_timesteps | 1472500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0446 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 531 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294600 |\n", "| time_elapsed | 7893 |\n", "| total_timesteps | 1473000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0673 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 532 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294700 |\n", "| time_elapsed | 7895 |\n", "| total_timesteps | 1473500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0308 |\n", "| value_loss | 0.00244 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294800 |\n", "| time_elapsed | 7898 |\n", "| total_timesteps | 1474000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0333 |\n", "| value_loss | 0.00236 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 294900 |\n", "| time_elapsed | 7900 |\n", "| total_timesteps | 1474500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.038 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295000 |\n", "| time_elapsed | 7903 |\n", "| total_timesteps | 1475000 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0351 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295100 |\n", "| time_elapsed | 7905 |\n", "| total_timesteps | 1475500 |\n", "| train/ | |\n", "| entropy_loss | -1.17 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0572 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295200 |\n", "| time_elapsed | 7908 |\n", "| total_timesteps | 1476000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0328 |\n", "| value_loss | 0.00224 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295300 |\n", "| time_elapsed | 7911 |\n", "| total_timesteps | 1476500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.04 |\n", "| value_loss | 0.879 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295400 |\n", "| time_elapsed | 7913 |\n", "| total_timesteps | 1477000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 2.42 |\n", "| value_loss | 2.55 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295500 |\n", "| time_elapsed | 7916 |\n", "| total_timesteps | 1477500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0477 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295600 |\n", "| time_elapsed | 7918 |\n", "| total_timesteps | 1478000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.043 |\n", "| value_loss | 0.00233 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295700 |\n", "| time_elapsed | 7921 |\n", "| total_timesteps | 1478500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0462 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295800 |\n", "| time_elapsed | 7924 |\n", "| total_timesteps | 1479000 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0371 |\n", "| value_loss | 0.00237 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 295900 |\n", "| time_elapsed | 7926 |\n", "| total_timesteps | 1479500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.623 |\n", "| value_loss | 0.698 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296000 |\n", "| time_elapsed | 7929 |\n", "| total_timesteps | 1480000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.055 |\n", "| value_loss | 0.00243 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296100 |\n", "| time_elapsed | 7931 |\n", "| total_timesteps | 1480500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -2.38e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.173 |\n", "| value_loss | 0.173 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296200 |\n", "| time_elapsed | 7934 |\n", "| total_timesteps | 1481000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.0989 |\n", "| value_loss | 0.174 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296300 |\n", "| time_elapsed | 7936 |\n", "| total_timesteps | 1481500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0536 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296400 |\n", "| time_elapsed | 7939 |\n", "| total_timesteps | 1482000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0529 |\n", "| value_loss | 0.00242 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296500 |\n", "| time_elapsed | 7941 |\n", "| total_timesteps | 1482500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0526 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296600 |\n", "| time_elapsed | 7944 |\n", "| total_timesteps | 1483000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0451 |\n", "| value_loss | 0.00238 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 540 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296700 |\n", "| time_elapsed | 7946 |\n", "| total_timesteps | 1483500 |\n", "| train/ | |\n", "| entropy_loss | -1.18 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0509 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296800 |\n", "| time_elapsed | 7949 |\n", "| total_timesteps | 1484000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0459 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 296900 |\n", "| time_elapsed | 7951 |\n", "| total_timesteps | 1484500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0698 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 535 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297000 |\n", "| time_elapsed | 7954 |\n", "| total_timesteps | 1485000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0551 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297100 |\n", "| time_elapsed | 7956 |\n", "| total_timesteps | 1485500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0499 |\n", "| value_loss | 0.0022 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.8 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297200 |\n", "| time_elapsed | 7959 |\n", "| total_timesteps | 1486000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0389 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 533 |\n", "| ep_rew_mean | 18.9 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297300 |\n", "| time_elapsed | 7961 |\n", "| total_timesteps | 1486500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0308 |\n", "| value_loss | 0.00223 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297400 |\n", "| time_elapsed | 7964 |\n", "| total_timesteps | 1487000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0384 |\n", "| value_loss | 0.0023 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 534 |\n", "| ep_rew_mean | 19.1 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297500 |\n", "| time_elapsed | 7967 |\n", "| total_timesteps | 1487500 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0588 |\n", "| value_loss | 0.00233 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297600 |\n", "| time_elapsed | 7969 |\n", "| total_timesteps | 1488000 |\n", "| train/ | |\n", "| entropy_loss | -1.19 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0604 |\n", "| value_loss | 0.00228 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297700 |\n", "| time_elapsed | 7972 |\n", "| total_timesteps | 1488500 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.03 |\n", "| value_loss | 0.00221 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297800 |\n", "| time_elapsed | 7974 |\n", "| total_timesteps | 1489000 |\n", "| train/ | |\n", "| entropy_loss | -1.2 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0633 |\n", "| value_loss | 0.0021 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 297900 |\n", "| time_elapsed | 7977 |\n", "| total_timesteps | 1489500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0375 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298000 |\n", "| time_elapsed | 7979 |\n", "| total_timesteps | 1490000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 5.96e-08 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0642 |\n", "| value_loss | 0.00211 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298100 |\n", "| time_elapsed | 7982 |\n", "| total_timesteps | 1490500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0365 |\n", "| value_loss | 0.00217 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298200 |\n", "| time_elapsed | 7984 |\n", "| total_timesteps | 1491000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0611 |\n", "| value_loss | 0.00205 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.2 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298300 |\n", "| time_elapsed | 7987 |\n", "| total_timesteps | 1491500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00207 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298400 |\n", "| time_elapsed | 7989 |\n", "| total_timesteps | 1492000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 1.1 |\n", "| value_loss | 0.7 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298500 |\n", "| time_elapsed | 7992 |\n", "| total_timesteps | 1492500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.066 |\n", "| value_loss | 0.00235 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.3 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298600 |\n", "| time_elapsed | 7994 |\n", "| total_timesteps | 1493000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0333 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298700 |\n", "| time_elapsed | 7997 |\n", "| total_timesteps | 1493500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0579 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.4 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298800 |\n", "| time_elapsed | 7999 |\n", "| total_timesteps | 1494000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.0024 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 298900 |\n", "| time_elapsed | 8002 |\n", "| total_timesteps | 1494500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0378 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "-------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299000 |\n", "| time_elapsed | 8004 |\n", "| total_timesteps | 1495000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | -1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0581 |\n", "| value_loss | 0.00248 |\n", "-------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299100 |\n", "| time_elapsed | 8007 |\n", "| total_timesteps | 1495500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0561 |\n", "| value_loss | 0.00246 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 538 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299200 |\n", "| time_elapsed | 8010 |\n", "| total_timesteps | 1496000 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0771 |\n", "| value_loss | 0.00249 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299300 |\n", "| time_elapsed | 8012 |\n", "| total_timesteps | 1496500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0361 |\n", "| value_loss | 0.00245 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299400 |\n", "| time_elapsed | 8014 |\n", "| total_timesteps | 1497000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 1.19e-07 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0504 |\n", "| value_loss | 0.00232 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299500 |\n", "| time_elapsed | 8017 |\n", "| total_timesteps | 1497500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | 0.963 |\n", "| value_loss | 0.88 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299600 |\n", "| time_elapsed | 8019 |\n", "| total_timesteps | 1498000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0533 |\n", "| value_loss | 0.00229 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 537 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299700 |\n", "| time_elapsed | 8022 |\n", "| total_timesteps | 1498500 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0393 |\n", "| value_loss | 0.00227 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 536 |\n", "| ep_rew_mean | 19.5 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299800 |\n", "| time_elapsed | 8024 |\n", "| total_timesteps | 1499000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0409 |\n", "| value_loss | 0.00231 |\n", "------------------------------------\n", "------------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 539 |\n", "| ep_rew_mean | 19.6 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 299900 |\n", "| time_elapsed | 8027 |\n", "| total_timesteps | 1499500 |\n", "| train/ | |\n", "| entropy_loss | -1.21 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0649 |\n", "| value_loss | 0.00236 |\n", "------------------------------------\n", "Eval num_timesteps=1500000, episode_reward=1.00 +/- 0.00\n", "Episode length: 420.00 +/- 0.00\n", "------------------------------------\n", "| eval/ | |\n", "| mean_ep_length | 420 |\n", "| mean_reward | 1 |\n", "| time/ | |\n", "| total_timesteps | 1500000 |\n", "| train/ | |\n", "| entropy_loss | -1.22 |\n", "| explained_variance | 0 |\n", "| learning_rate | 0.0007 |\n", "| policy_loss | -0.0315 |\n", "| value_loss | 0.00213 |\n", "------------------------------------\n", "---------------------------------\n", "| rollout/ | |\n", "| ep_len_mean | 541 |\n", "| ep_rew_mean | 19.7 |\n", "| time/ | |\n", "| fps | 186 |\n", "| iterations | 300000 |\n", "| time_elapsed | 8041 |\n", "| total_timesteps | 1500000 |\n", "---------------------------------\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Train the model\n", "model.learn(total_timesteps=NUM_TIMESTEPS, callback=callback_list, tb_log_name=\"./tb/\")" ] }, { "cell_type": "code", "execution_count": 9, "id": "7f8c4c28", "metadata": { "execution": { "iopub.execute_input": "2024-05-14T16:53:33.124854Z", "iopub.status.busy": "2024-05-14T16:53:33.123624Z", "iopub.status.idle": "2024-05-14T16:53:33.541447Z", "shell.execute_reply": "2024-05-14T16:53:33.540411Z" }, "papermill": { "duration": 0.724264, "end_time": "2024-05-14T16:53:33.543838", "exception": false, "start_time": "2024-05-14T16:53:32.819574", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# Save the model and policy for future loading and training\n", "model.save(MODEL_FILE_NAME)\n", "model.policy.save(POLICY_FILE_NAME)" ] } ], "metadata": { "kaggle": { "accelerator": "nvidiaTeslaT4", "dataSources": [], "dockerImageVersionId": 30699, "isGpuEnabled": true, "isInternetEnabled": true, "language": "python", "sourceType": "notebook" }, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.13" }, "papermill": { "default_parameters": {}, "duration": 8131.216961, "end_time": "2024-05-14T16:53:36.392099", "environment_variables": {}, "exception": null, "input_path": "__notebook__.ipynb", "output_path": "__notebook__.ipynb", "parameters": {}, "start_time": "2024-05-14T14:38:05.175138", "version": "2.5.0" } }, "nbformat": 4, "nbformat_minor": 5 }