Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,79 @@
+---
+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: 3033.34 +/- 20.17
+      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 qgallouedec -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 qgallouedec -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 qgallouedec
+```
+
+## 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)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - HalfCheetahBulletEnv-v0
+  - - 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
+    - -1
+  - - 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
+    - 2975909910
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/HalfCheetahBulletEnv-v0__sac__2975909910__1671923344
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

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 @@
+{}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26102c7b2381ef1039c367bb1ea18297b5f97548a4befe83c8f52d816e389a1a
+size 1215238

results.json

@@ -0,0 +1 @@
+{"mean_reward": 3033.3427114, "std_reward": 20.173427257673918, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:18:42.406759"}

sac-HalfCheetahBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaa84c5b8a9ddf5d81c37c08f479c41980977606d90ff7e6525eadd83fe840c
+size 5946466

sac-HalfCheetahBulletEnv-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

sac-HalfCheetahBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e41e419e79437f1d623d0c4a31be2c00f24e99fecaef11649979079aba407aa
+size 1083238

sac-HalfCheetahBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a2613ad8c3a6f7b2f95797d15b43c7336a0ebfecbafefe1cb6877d7e0efd88
+size 2150201

sac-HalfCheetahBulletEnv-v0/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=",
+        "__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 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 0x7f540d112ca0>",
+        "_build": "<function SACPolicy._build at 0x7f540d112d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f540d112dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f540d112e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f540d112ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f540d112f70>",
+        "forward": "<function SACPolicy.forward at 0x7f540d11a040>",
+        "_predict": "<function SACPolicy._predict at 0x7f540d11a0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f540d11a160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f540d11b200>"
+    },
+    "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",
+        "_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]",
+        "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]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            6
+        ],
+        "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)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1671923347009178316,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/HalfCheetahBulletEnv-v0__sac__2975909910__1671923344/HalfCheetahBulletEnv-v0",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV3QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZoAAAAAAAAAIYNjL4AAAAAAACAP6KlXz8AAAAAGxK2PQAAAIAqvgs+bVWIv0JSij6q2Ac/kZtcPx1ijr/Y5Q+8wweAP7t21LpuPCM/nmAvPtSCQT/yt3u+AAAAAAAAAAAAAAAAAACAPwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSxqGlIwBQ5R0lFKULg=="
+    },
+    "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 990000,
+    "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",
+        "__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 0x7f540d16a430>",
+        "add": "<function ReplayBuffer.add at 0x7f540d16a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f540d16a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f540d16a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f540d5b5a00>"
+    },
+    "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,
+    "_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 sha256:3862fa3a00675313c948611c82f6f5510a193c1e4ff5343c8cd3a7de1c885e7b
+size 1507

sac-HalfCheetahBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81eaed2409859f424c28d433e93933b57b32261c2047930c113f2501cb0de14
+size 2689992

sac-HalfCheetahBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3dbbeb69ae099f8c4ef2cadd7175eb0dc0fb6e54753d738ce221c5eec8d2ed
+size 747

sac-HalfCheetahBulletEnv-v0/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cae120921ec78ad439d812275428be2d02c8154ee61e02864b19466a7e6296d
+size 34195