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 +1,68 @@
+---
+library_name: stable-baselines3
+tags:
+- HalfCheetahBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 2785.96 +/- 14.09
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HalfCheetahBulletEnv-v0
+      type: HalfCheetahBulletEnv-v0
+---
+
+# **SAC** Agent playing **HalfCheetahBulletEnv-v0**
+This is a trained model of a **SAC** agent playing **HalfCheetahBulletEnv-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 sac --env HalfCheetahBulletEnv-v0 -orga sb3 -f logs/
+python enjoy.py --algo sac --env HalfCheetahBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env HalfCheetahBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env HalfCheetahBulletEnv-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('env_wrapper', 'sb3_contrib.common.wrappers.TimeFeatureWrapper'),
+             ('gamma', 0.98),
+             ('gradient_steps', 64),
+             ('learning_rate', 0.00073),
+             ('learning_starts', 10000),
+             ('n_timesteps', 1000000.0),
+             ('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
+    - HalfCheetahBulletEnv-v0
+  - - 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
+    - 2654485775
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - true
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 300000
+  - - ent_coef
+    - auto
+  - - env_wrapper
+    - sb3_contrib.common.wrappers.TimeFeatureWrapper
+  - - gamma
+    - 0.98
+  - - gradient_steps
+    - 64
+  - - learning_rate
+    - 0.00073
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 1000000.0
+  - - 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 sha256:04b32242e9f85f79a0e0237527974105afc54413f45cf97925210ccf0ae623b4
+size 1055860

results.json

@@ -0,0 +1 @@
+{"mean_reward": 2785.9604036000005, "std_reward": 14.091151998286982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:53:11.122650"}

sac-HalfCheetahBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c6502954a1c6f96231e703b5f70b75ca4b49800102371399209b00eb4a62bd
+size 5958887

sac-HalfCheetahBulletEnv-v0/_stable_baselines3_version

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

sac-HalfCheetahBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b2d3fa824e023bc7fa5369f9be49b14484ba281d5f235338bfb2dcbf018319
+size 1084603

sac-HalfCheetahBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ed6de5f00fed303d241a68d8cb8162e6d9292fb019b3531e9ee564820e62d6
+size 2153629

sac-HalfCheetahBulletEnv-v0/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 0x7f0d49a7d710>",
+        "_build": "<function SACPolicy._build at 0x7f0d49a7d7a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f0d49a7d830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f0d49a7d8c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f0d49a7d950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f0d49a7d9e0>",
+        "forward": "<function SACPolicy.forward at 0x7f0d49a7da70>",
+        "_predict": "<function SACPolicy._predict at 0x7f0d49a7db00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f0d49a7db90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0d49a5fab0>"
+    },
+    "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 -inf -inf   0.]",
+        "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 inf inf  1.]",
+        "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\n False False  True]",
+        "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\n False False  True]",
+        "_np_random": null,
+        "_shape": [
+            27
+        ]
+    },
+    "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": 1614621300.2573972,
+    "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:": "gASV9gAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLG4aUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNscY6MvgAAAAAAAIA/5FkgPwAAAADRrxq+AAAAgBtcTj8dnYC/cN4IPQ9ogL8ODXk8ILLZPbC9UD/4F1A/LDCFPbZoTz8hW4I9dC7jPvtmNT4AAIA/AAAAAAAAAAAAAAAAAAAAAAAAAABvEoM6lHSUYi4="
+    },
+    "_episode_num": 1000,
+    "use_sde": true,
+    "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": 990016,
+    "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 0x7f0d49edeb90>",
+        "add": "<function ReplayBuffer.add at 0x7f0d49edec20>",
+        "sample": "<function ReplayBuffer.sample at 0x7f0d49a457a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f0d49a45830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f0d49f355d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLQGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

sac-HalfCheetahBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b267034250ae077603f1c01f847794cb01b0e09f99d7db0e468f1f7c7934b4f1
+size 1255

sac-HalfCheetahBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1cba7ce68d7f322790be6e3986b823d52cfc8f282eed67b548442a6efe11d8b
+size 2697992

sac-HalfCheetahBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5510a587848d74cb11c5e158a54a83635aab171e7c4e529efc28093f9670e458
+size 747

sac-HalfCheetahBulletEnv-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

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e4b357332bb9a1fd94eb5f5f5d62c7b4c42d3a4b57d867cbe21c38744239774
+size 47883