Initial commit

.gitattributes

@@ -25,3 +25,4 @@ 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

README.md

@@ -0,0 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- BipedalWalker-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 300.53 +/- 0.76
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BipedalWalker-v3
+      type: BipedalWalker-v3
+---
+
+# **SAC** Agent playing **BipedalWalker-v3**
+This is a trained model of a **SAC** agent playing **BipedalWalker-v3**
+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 sac --env BipedalWalker-v3 -orga sb3 -f logs/
+python enjoy.py --algo sac --env BipedalWalker-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env BipedalWalker-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env BipedalWalker-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 0.00073),
+             ('learning_starts', 10000),
+             ('n_timesteps', 500000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(log_std_init=-3, net_arch=[400, 300])'),
+             ('tau', 0.02),
+             ('train_freq', 64),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - BipedalWalker-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - rl-trained-agents/
+  - - log_interval
+    - -1
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - num_threads
+    - -1
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3337420815
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - 0.00073
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 500000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-3, net_arch=[400, 300])
+  - - tau
+    - 0.02
+  - - train_freq
+    - 64
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3ed3abb7d56df492ade9b613dafd05d356226616e80dac1c44f6632d32eaab
+size 425498

results.json

@@ -0,0 +1 @@
+{"mean_reward": 300.5344519, "std_reward": 0.7618170684146451, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T19:05:03.197373"}

sac-BipedalWalker-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5444c64c159a8af1320809cbc6a2e843cefeb83430933c6a3a1ffb6b31509de4
+size 5867335

sac-BipedalWalker-v3/_stable_baselines3_version

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

sac-BipedalWalker-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4209d5e1e1596ae8a2b398c5bc43b129925e4b2af64195c83e9f642678fc76f0
+size 1065467

sac-BipedalWalker-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7213d39852db351410c0ad60f8b87d3638377be6f1fd5807ad9229407cd2794
+size 2121629

sac-BipedalWalker-v3/data

@@ -0,0 +1,122 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\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()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
+        "__init__": "<function SACPolicy.__init__ at 0x7fe36633d710>",
+        "_build": "<function SACPolicy._build at 0x7fe36633d7a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fe36633d830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fe36633d8c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fe36633d950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fe36633d9e0>",
+        "forward": "<function SACPolicy.forward at 0x7fe36633da70>",
+        "_predict": "<function SACPolicy._predict at 0x7fe36633db00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fe36633db90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fe366320ab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "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 -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 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 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 False False]",
+        "_np_random": null,
+        "_shape": [
+            24
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1.]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            4
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 500032,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614710447.004581,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASV6gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLGIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNgza7dPeP1HL3OtvY+N4+BvAexVb8AABC0v5VsPwAAAAAAAAAAcXzkPgEAgD/wwyG/q6oqNAAAAADAy8U+MRPHPlH6zD6C/tc+17PpPrm8Az/Tthw/SE9IPwAAgD8AAIA/lHSUYi4="
+    },
+    "_episode_num": 532,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -6.4000000000064e-05,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 490048,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 64,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device:\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fe36679fb90>",
+        "add": "<function ReplayBuffer.add at 0x7fe36679fc20>",
+        "sample": "<function ReplayBuffer.sample at 0x7fe3663067a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe366306830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fe3667f65d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -4.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

sac-BipedalWalker-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d8f26cdd9c2fc9cd7bd598f8f61e2551916e20b7de73916fd2eb010d3d939e
+size 1255

sac-BipedalWalker-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d15542848b597a4872f16cd53d9262d02dd93bae18dec5f8220e8bd707bbf1c
+size 2656328

sac-BipedalWalker-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40882337613e55df69ca2d68cf1edb91907729b7f692f19fe2f8b3ff0864b82
+size 747

sac-BipedalWalker-v3/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

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8ef983d84cccf16cb0c10a61ecd33eb698eb0c2b5208b61e27187fec0a9af6
+size 24501