Huggy

README.md

@@ -1,37 +1,35 @@
 ---
-library_name: stable-baselines3
+library_name: ml-agents
 tags:
-- LunarLander-v2
+- Huggy
 - deep-reinforcement-learning
 - reinforcement-learning
-- stable-baselines3
-model-index:
-- name: PPO
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
-    metrics:
-    - type: mean_reward
-      value: 245.61 +/- 22.19
-      name: mean_reward
-      verified: false
+- ML-Agents-Huggy
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+  # **ppo** Agent playing **Huggy**
+  This is a trained model of a **ppo** agent playing **Huggy**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
 
-...
-```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: Dhanraj1503/deep_reinforcement_learning
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f038d23c4c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f038d23c550>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f038d23c5e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f038d23c670>", "_build": "<function ActorCriticPolicy._build at 0x7f038d23c700>", "forward": "<function ActorCriticPolicy.forward at 0x7f038d23c790>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f038d23c820>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f038d23c8b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f038d23c940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f038d23c9d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f038d23ca60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f038d23caf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f038d3e33c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705301315155060306, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAGZyNT3sOeO5oiIcO1FvxDVi9ps6IsQ2ugAAgD8AAIA/ZoGSPCnwL7qfApI6K43UtAEMOTsm3Ky5AACAPwAAgD9N7Si9rmWxuiYdnznS7Ge2Xwv7OXNhYbUAAIA/AACAPzOir73Rnn0/SnCoOefUjr7BftG7DiIGugAAAAAAAAAAZuOwvUPGPz1X+CM9hoFsvo3cfbws8oM9AAAAAAAAAADmz489jw4CuusRfTkkg0Q0J1tUu62qkrgAAIA/AACAP2bWuLspHA26+PfvOo9UPjY73wc7zwULugAAgD8AAIA/zbS3u4Wz67mCnZe60AIOtkBatLommrI5AACAPwAAgD/zPCY++A+SP6KpBz0KsqC+9Cc9Ph1FV70AAAAAAAAAAE3Zwz17Lqi6o0/fOSSGUbZfJEE6zoX/uAAAgD8AAIA/AEBuusPVZboCWNY6HLHENQzzMjs+zvq5AACAPwAAgD9mWp69KchFuhadojv3j7M2Ajf2ORdZrzUAAIA/AACAPybmez7XF1o/hzkevucUk77QY4U9uPENvgAAAAAAAAAAc7KqPVz/abqKij45WVy/NKzWdTsDHFu4AACAPwAAgD9mnOS8WNqFPb3v0z0CkMu9xmtbPDZ2LD0AAAAAAAAAAJqKrTyPWky6CrHWOAcKODS7FQk7ktf0twAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  Huggy:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 200000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 15
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 1000
+    summary_freq: 50000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./trained-envs-executables/linux/Huggy/Huggy
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Huggy
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/timers.json

@@ -0,0 +1,47 @@
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1705323677",
+        "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1705323678"
+    },
+    "total": 0.2886882970000215,
+    "count": 1,
+    "self": 0.08845060800001647,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05506683199996587,
+            "count": 1,
+            "self": 0.05506683199996587
+        },
+        "TrainerController.start_learning": {
+            "total": 0.14517085700003918,
+            "count": 1,
+            "self": 0.0004509939999479684,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 0.1447030489999861,
+                    "count": 1,
+                    "self": 0.1447030489999861
+                },
+                "trainer_threads": {
+                    "total": 1.6000000186977559e-06,
+                    "count": 1,
+                    "self": 1.6000000186977559e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 1.521400008641649e-05,
+                    "count": 1,
+                    "self": 1.521400008641649e-05
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,7 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.2+cu121"
+    }
+}