Initial commit

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2DBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 1055.77 +/- 924.98
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2DBulletEnv-v0
+      type: Walker2DBulletEnv-v0
+---
+
+# **TRPO** Agent playing **Walker2DBulletEnv-v0**
+This is a trained model of a **TRPO** agent playing **Walker2DBulletEnv-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo trpo --env Walker2DBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env Walker2DBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env Walker2DBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env Walker2DBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('cg_damping', 0.1),
+             ('cg_max_steps', 25),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.99),
+             ('learning_rate', 0.001),
+             ('n_critic_updates', 20),
+             ('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 2000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('sub_sampling_factor', 1),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - Walker2DBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 50000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 10
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3437424136
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - cg_damping
+    - 0.1
+  - - cg_max_steps
+    - 25
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - 0.001
+  - - n_critic_updates
+    - 20
+  - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 2000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - sub_sampling_factor
+    - 1

env_kwargs.yml

@@ -0,0 +1 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be758ebabf2faa980577cc77862c6f1bed09eeabb2c03ea8f213fe73130d7104
+size 1164370

results.json

@@ -0,0 +1 @@
+{"mean_reward": 1055.7737765, "std_reward": 924.9826163222573, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:13:21.567130"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9ded1f4217dfb1c29325c89e69acd0e08195535884fa7e99db2c9a032750ad
+size 123801

trpo-Walker2DBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90af910791c46f09a58ffe4e171fcb4b91dd7ada0290688e80aa8a634e6b398d
+size 119236

trpo-Walker2DBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

trpo-Walker2DBulletEnv-v0/data

@@ -0,0 +1,102 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f1941d51950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f1941d519e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f1941d51a70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f1941d51b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f1941d51b90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f1941d51c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f1941d51cb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f1941d51d40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f1941d51dd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f1941d51e60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f1941d51ef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f1941da2840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False]",
+        "_np_random": null,
+        "_shape": [
+            22
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            6
+        ]
+    },
+    "n_envs": 2,
+    "num_timesteps": 2000896,
+    "_total_timesteps": 2000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640776159.6669414,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gASV0QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAUsBSxNDBIgAUwCUToWUKYwBX5SFlIxRL2hvbWUvYW50b25pbi9Eb2N1bWVudHMvZGxyL3JsL3RvcmNoeS1iYXNlbGluZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxRL2hvbWUvYW50b25pbi9Eb2N1bWVudHMvZGxyL3JsL3RvcmNoeS1iYXNlbGluZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgYjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9QYk3S8an8hZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVigAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAgAAlHSUYi4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVOgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwJLFoaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOwAAAAAAAAAAAAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIDnvoU/AAAAAPtchT8AAAAAgLDjPQAAAACi/4I/AAAAAK/qgD8AAAAAzlGWvQAAAAAAAAAAAAAAAAAAAAAAAAAAAACAPwAAAAAAAAAAAAAAAAAAAAAAAACAOIlxPwAAAACpVnc/AAAAAG7/kT0AAAAAhMt9PwAAAAAdv3w/AAAAAEODLzwAAAAAAAAAAAAAAACUdJRiLg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00044800000000000395,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 977,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.0,
+    "max_grad_norm": 0.0,
+    "normalize_advantage": true,
+    "batch_size": 128,
+    "cg_max_steps": 25,
+    "cg_damping": 0.1,
+    "line_search_shrinking_factor": 0.8,
+    "line_search_max_iter": 10,
+    "target_kl": 0.01,
+    "n_critic_updates": 20,
+    "sub_sampling_factor": 1
+}

trpo-Walker2DBulletEnv-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba2d0a2c3206ffd2dda5d25838fed04eb11145fcca5224b9e6058999698290b
+size 48897

trpo-Walker2DBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1478f141245d474b1c501c246601ee348d820e7770ae305051ba1d62b56e7fa3
+size 51198

trpo-Walker2DBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

trpo-Walker2DBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-44-generic-x86_64-with-debian-bullseye-sid #49~20.04.1-Ubuntu SMP Wed May 18 18:44:28 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16ebbae67e662ba3a1682223c1aefac83d81694a145bf92a4a9c308dfb02b9b4
+size 5050