Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- HalfCheetahBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HalfCheetahBulletEnv-v0
+      type: HalfCheetahBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 3038.56 +/- 42.27
+      name: mean_reward
+      verified: false
+---
+
+# **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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo sac --env HalfCheetahBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo sac --env HalfCheetahBulletEnv-v0  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo sac --env HalfCheetahBulletEnv-v0 -orga Emperor-WS -f logs/
+python -m rl_zoo3.enjoy --algo sac --env HalfCheetahBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env HalfCheetahBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env HalfCheetahBulletEnv-v0 -f logs/ -orga Emperor-WS
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 300000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.98),
+             ('gradient_steps', 8),
+             ('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', 8),
+             ('use_sde', True),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - HalfCheetahBulletEnv-v0
+  - - env_kwargs
+    - null
+  - - eval_env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs/
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - 1000000
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3832775135
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - rl-trained-agents/sac/HalfCheetahBulletEnv-v0_1/HalfCheetahBulletEnv-v0.zip
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

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
+    - 8
+  - - 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
+    - 8
+  - - use_sde
+    - true

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d0dc1a647834ae8cb3b618a8c72955f06b23ae55d520d8623542a1291464ef
+size 1191850

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3038.5576853000002, "std_reward": 42.26724311604498, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-27T01:39:44.261539"}

sac-HalfCheetahBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d708350c532e07ef81220b864902714ca4f1add3c17204e418514d75ab929bfb
+size 5946007

sac-HalfCheetahBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.0a2

sac-HalfCheetahBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e320688b9e23b9a5077527b49b1a7f2903f1ab084bb8c4a4ee24add164ba864a
+size 1083671

sac-HalfCheetahBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d5a574acf9e12ccb634bde2215a95b3c8ebf5fe85bcc4b7abb53156ef840e7
+size 2150634

sac-HalfCheetahBulletEnv-v0/data

@@ -0,0 +1,138 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.sac.policies",
+        "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
+        "__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 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 0x7e6a81b81090>",
+        "_build": "<function SACPolicy._build at 0x7e6a81b81120>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7e6a81b811b0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7e6a81b81240>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7e6a81b812d0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7e6a81b81360>",
+        "forward": "<function SACPolicy.forward at 0x7e6a81b813f0>",
+        "_predict": "<function SACPolicy._predict at 0x7e6a81b81480>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7e6a81b81510>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e6a81b89cc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "log_std_init": -3,
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": true
+    },
+    "num_timesteps": 501168,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1708990741214169465,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV3QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZoAAAAAAAAAA+xIr4AAAAAAACAPzZsnT8AAAAAAoZ6PgAAAAAnopG9s0WEPoErQD962Sk++v+jv6B1IL/tbGg/Zq56P+a3v7uFWFA/+IaaPkthgD+KYM68AAAAAAAAAAAAAAAAAACAPwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSxqGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 501,
+    "use_sde": true,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.49883200000000005,
+    "_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": 1481160,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVgwIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWGgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksahZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWGgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJRoFUsahZRoGXSUUpSMBl9zaGFwZZRLGoWUjANsb3eUaBEolmgAAAAAAAAAAACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP8AAID/AACA/wAAgP+UaAtLGoWUaBl0lFKUjARoaWdolGgRKJZoAAAAAAAAAAAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/AACAfwAAgH8AAIB/lGgLSxqFlGgZdJRSlIwIbG93X3JlcHKUjAQtaW5mlIwJaGlnaF9yZXBylIwDaW5mlIwKX25wX3JhbmRvbZROdWIu",
+        "dtype": "float32",
+        "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]",
+        "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]",
+        "_shape": [
+            26
+        ],
+        "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]",
+        "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]",
+        "low_repr": "-inf",
+        "high_repr": "inf",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[-1. -1. -1. -1. -1. -1.]",
+        "high": "[1. 1. 1. 1. 1. 1.]",
+        "low_repr": "-1.0",
+        "high_repr": "1.0",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.02,
+    "gamma": 0.98,
+    "gradient_steps": 8,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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: PyTorch 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        Cannot be used in combination with handle_timeout_termination.\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 0x7e6a49ad52d0>",
+        "add": "<function ReplayBuffer.add at 0x7e6a49ad5360>",
+        "sample": "<function ReplayBuffer.sample at 0x7e6a49ad53f0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7e6a49ad5480>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7e6a49ad5510>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7e6a49c50a00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLCGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -6.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_action_repeat": [
+        null
+    ],
+    "surgeon": null,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "_last_action": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVjQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYYAAAAAAAAAOjKej9wTkW9BGpJP4jhQj+a6iQ/SK9cPpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsGhpSMAUOUdJRSlC4="
+    }
+}

sac-HalfCheetahBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf47a43cdf8b5d4dd7be0bc5243f66bc7f9ff463eda831ca5197db2a96383ef6
+size 1940

sac-HalfCheetahBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae9d4ebecee9ca9c9c15a8cc5015588046d7ac78611a61ed13676dc5634e8549
+size 2690425

sac-HalfCheetahBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47897ae03cca2c55994de8cdcfec8387848878c018d6238aa46171cfd7818a84
+size 1180

sac-HalfCheetahBulletEnv-v0/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
+- Python: 3.10.13
+- Stable-Baselines3: 2.3.0a2
+- PyTorch: 2.1.2
+- GPU Enabled: True
+- Numpy: 1.26.3
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.0
+- OpenAI Gym: 0.26.2

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3705a82e599712c0233cd8226d72482e907abfcbe97c2a946f2a4396efc820
+size 17665