{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.919926643371582, "min": 0.919926643371582, "max": 2.851696014404297, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8834.0556640625, "min": 8834.0556640625, "max": 29298.32421875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.908611297607422, "min": 0.5113367438316345, "max": 12.908611297607422, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2517.17919921875, "min": 99.19932556152344, "max": 2586.862060546875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06706031959323559, "min": 0.06233772589314636, "max": 0.07526508580171959, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26824127837294237, "min": 0.24935090357258544, "max": 0.36429840017380605, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18970471065418393, "min": 0.15928035228987975, "max": 0.26900793378259624, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7588188426167357, "min": 0.637121409159519, "max": 1.3312138862469618, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.795454545454547, "min": 3.840909090909091, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1135.0, "min": 169.0, "max": 1412.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.795454545454547, "min": 3.840909090909091, "max": 25.795454545454547, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1135.0, "min": 169.0, "max": 1412.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713794597", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713795212" }, "total": 614.9785298630001, "count": 1, "self": 0.9514457730000458, "children": { "run_training.setup": { "total": 0.06767494700000043, "count": 1, "self": 0.06767494700000043 }, "TrainerController.start_learning": { "total": 613.959409143, "count": 1, "self": 0.7994793050012277, "children": { "TrainerController._reset_env": { "total": 3.091724329999977, "count": 1, "self": 3.091724329999977 }, "TrainerController.advance": { "total": 609.8828544669987, "count": 18218, "self": 0.4291326649935172, "children": { "env_step": { "total": 609.4537218020051, "count": 18218, "self": 401.19708502600605, "children": { "SubprocessEnvManager._take_step": { "total": 207.82708068100624, "count": 18218, "self": 2.3334349850019294, "children": { "TorchPolicy.evaluate": { "total": 205.4936456960043, "count": 18218, "self": 205.4936456960043 } } }, "workers": { "total": 0.4295560949928472, "count": 18218, "self": 0.0, "children": { "worker_root": { "total": 611.9707827089973, "count": 18218, "is_parallel": true, "self": 297.4001227410005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0059696389999999155, "count": 1, "is_parallel": true, "self": 0.004083846999947127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018857920000527884, "count": 10, "is_parallel": true, "self": 0.0018857920000527884 } } }, "UnityEnvironment.step": { "total": 0.0489348329999757, "count": 1, "is_parallel": true, "self": 0.0008529769999086056, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005048720000218054, "count": 1, "is_parallel": true, "self": 0.0005048720000218054 }, "communicator.exchange": { "total": 0.04505451800002902, "count": 1, "is_parallel": true, "self": 0.04505451800002902 }, "steps_from_proto": { "total": 0.0025224660000162658, "count": 1, "is_parallel": true, "self": 0.000511957999947299, "children": { "_process_rank_one_or_two_observation": { "total": 0.002010508000068967, "count": 10, "is_parallel": true, "self": 0.002010508000068967 } } } } } } }, "UnityEnvironment.step": { "total": 314.5706599679968, "count": 18217, "is_parallel": true, "self": 14.877513691999184, "children": { "UnityEnvironment._generate_step_input": { "total": 7.8894535849985346, "count": 18217, "is_parallel": true, "self": 7.8894535849985346 }, "communicator.exchange": { "total": 244.45174629700523, "count": 18217, "is_parallel": true, "self": 244.45174629700523 }, "steps_from_proto": { "total": 47.35194639399384, "count": 18217, "is_parallel": true, "self": 9.302919725987636, "children": { "_process_rank_one_or_two_observation": { "total": 38.049026668006206, "count": 182170, "is_parallel": true, "self": 38.049026668006206 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00022004700008437794, "count": 1, "self": 0.00022004700008437794, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 601.3280046879536, "count": 911782, "is_parallel": true, "self": 21.52030656386887, "children": { "process_trajectory": { "total": 339.79638449308476, "count": 911782, "is_parallel": true, "self": 338.6902308030847, "children": { "RLTrainer._checkpoint": { "total": 1.106153690000042, "count": 4, "is_parallel": true, "self": 1.106153690000042 } } }, "_update_policy": { "total": 240.01131363099995, "count": 90, "is_parallel": true, "self": 65.32616851600267, "children": { "TorchPPOOptimizer.update": { "total": 174.68514511499728, "count": 4587, "is_parallel": true, "self": 174.68514511499728 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1851309940000192, "count": 1, "self": 0.0022586670000919185, "children": { "RLTrainer._checkpoint": { "total": 0.18287232699992728, "count": 1, "self": 0.18287232699992728 } } } } } } }