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 +1,58 @@
+---
+library_name: stable-baselines3
+tags:
+- Walker2d-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 3876.28 +/- 75.51
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Walker2d-v3
+      type: Walker2d-v3
+---
+
+# **SAC** Agent playing **Walker2d-v3**
+This is a trained model of a **SAC** agent playing **Walker2d-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 Walker2d-v3 -orga sb3 -f logs/
+python enjoy.py --algo sac --env Walker2d-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env Walker2d-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env Walker2d-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('use_sde', False),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - Walker2d-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - use_sde: false
+  - - log_folder
+    - logs/
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - 1000000
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 2
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 594371
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,9 @@
+!!python/object/apply:collections.OrderedDict
+- - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy
+  - - use_sde
+    - false

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2eca54e5995f766d2697652c2e711913fc21a453bafffd5f0bb151168c7baa4
+size 1450496

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3876.280908399999, "std_reward": 75.51175337541349, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:45:48.120655"}

sac-Walker2d-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb749324e176bd3aa3a18309bac05ca0e050f86aa461f4e4835c9be5c3ebc262
+size 3236549

sac-Walker2d-v3/_stable_baselines3_version

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

sac-Walker2d-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d6fcefef6a7acd601acac008b644617c3ffc1619d8d14b1dc1b2899c0380a9e
+size 592181

sac-Walker2d-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:610061da6ec0e99875c92be162a7aed0f8fe19251d06c74d4d35c4e930bde4f5
+size 1161629

sac-Walker2d-v3/data

@@ -0,0 +1,113 @@
+{
+    "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 0x7fe90532c710>",
+        "_build": "<function SACPolicy._build at 0x7fe90532c7a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fe90532c830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fe90532c8c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fe90532c950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fe90532c9e0>",
+        "forward": "<function SACPolicy.forward at 0x7fe90532ca70>",
+        "_predict": "<function SACPolicy._predict at 0x7fe90532cb00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fe90532cb90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fe90530fab0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf inf inf inf 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]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False]",
+        "_np_random": null,
+        "_shape": [
+            17
+        ]
+    },
+    "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": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1635497676.7438397,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQGUdJRiLg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVEgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLEYaUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOIPyT3wHst9D9VnlZwglDEP3rENxewV5q/FY3drgOxwj/MUa+shR/qP3G6VrTXuZq/tsWnTZbnuT+pPTzAbeTtP664Tci40uk/IKpkZ0Yb6j9mTwLolW0IQBDTAuQMWQpA3WsB2k/6CsAb+igs1pe2P1+Ssx/ZW/4/CuDMj2IUAsCTx6BbZUQLwJR0lGIu"
+    },
+    "_episode_num": 3137,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.005,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "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 0x7fe90578eb90>",
+        "add": "<function ReplayBuffer.add at 0x7fe90578ec20>",
+        "sample": "<function ReplayBuffer.sample at 0x7fe9052f57a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe9052f5830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fe9057e55d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "remove_time_limit_termination": false
+}

sac-Walker2d-v3/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991caf16729201f99cfbf797a14a2da00b0d59adcb1638e7cf063ba339c58aab
+size 1255

sac-Walker2d-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b59fa5c3657f168f957b251f1c14b84d03b6563362e4b175471d1f042473a0
+size 1459973

sac-Walker2d-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6379f4ba65e26fe9f55865b00f289abb40867d6a69ef940f04d50218ecdaa59e
+size 747

sac-Walker2d-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 sha256:17fed09f2bee376796fea56296d44d6869baa01aab7badfb9ab75740d3d4080f
+size 119459