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 +1,78 @@
+---
+library_name: stable-baselines3
+tags:
+- BipedalWalkerHardcore-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: BipedalWalkerHardcore-v3
+      type: BipedalWalkerHardcore-v3
+    metrics:
+    - type: mean_reward
+      value: -101.12 +/- 31.28
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **BipedalWalkerHardcore-v3**
+This is a trained model of a **SAC** agent playing **BipedalWalkerHardcore-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
+
+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 BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env BipedalWalkerHardcore-v3  -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 BipedalWalkerHardcore-v3 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env BipedalWalkerHardcore-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env BipedalWalkerHardcore-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env BipedalWalkerHardcore-v3 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 1000000),
+             ('ent_coef', 0.005),
+             ('gamma', 0.99),
+             ('gradient_steps', 1),
+             ('learning_rate', 'lin_7.3e-4'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 10000000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('tau', 0.01),
+             ('train_freq', 1),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - BipedalWalkerHardcore-v3
+  - - 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
+    - 172740193
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/BipedalWalkerHardcore-v3__sac__172740193__1671847712
+  - - 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 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 1000000
+  - - ent_coef
+    - 0.005
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - lin_7.3e-4
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 10000000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[400, 300])
+  - - tau
+    - 0.01
+  - - train_freq
+    - 1

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2aff105867a82f336375fa10bd1c3bb802e7720f490debc0833c0ce2a76e6a
+size 94405

results.json

@@ -0,0 +1 @@
+{"mean_reward": -101.11808319999997, "std_reward": 31.281940500456585, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:31:22.025191"}

sac-BipedalWalkerHardcore-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ee2b9ee70c164fecf13291658480c5f55f91ecaf32c024a70a2278d7302ba1
+size 5872414

sac-BipedalWalkerHardcore-v3/_stable_baselines3_version

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

sac-BipedalWalkerHardcore-v3/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c41d48ac0b101d7d73d195ce6a9f0452eae12d2d269f58557d9470a82176bd
+size 1068061

sac-BipedalWalkerHardcore-v3/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad1ce4641b5262ef682bc555a5b0db451ba164d43ea9994a64ca86532002b7f
+size 2124601

sac-BipedalWalkerHardcore-v3/data

@@ -0,0 +1,131 @@
+{
+    "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 0x7fcc6af92ca0>",
+        "_build": "<function SACPolicy._build at 0x7fcc6af92d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fcc6af92dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fcc6af92e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fcc6af92ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fcc6af92f70>",
+        "forward": "<function SACPolicy.forward at 0x7fcc6af9a040>",
+        "_predict": "<function SACPolicy._predict at 0x7fcc6af9a0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fcc6af9a160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fcc6af97e40>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            400,
+            300
+        ],
+        "use_sde": false
+    },
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            24
+        ],
+        "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
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            4
+        ],
+        "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)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 10000000,
+    "_total_timesteps": 10000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1671847714905042719,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/BipedalWalkerHardcore-v3__sac__172740193__1671847712/BipedalWalkerHardcore-v3",
+    "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:": "gAWV1QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZgAAAAAAAAAMvtpb1ENwg5AU5buoCs/rdv2I4/sJkROYynHL/QVRI5AACAP8JhHj+sv485vi8iv013s7kAAIA/4Tm1PsBItz7esr0+KkPJPiOU2z6Srvc+hMURP1wcNj+uEHo/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsYhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 8183,
+    "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 9990000,
+    "buffer_size": 1,
+    "batch_size": 256,
+    "learning_starts": 10000,
+    "tau": 0.01,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "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 0x7fcc6afea430>",
+        "add": "<function ReplayBuffer.add at 0x7fcc6afea4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fcc6afea550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fcc6afea5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fcc6afe0c00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -4.0,
+    "log_ent_coef": null,
+    "ent_coef": 0.005,
+    "target_update_interval": 1,
+    "ent_coef_optimizer": null,
+    "_action_repeat": [
+        null
+    ],
+    "surgeon": null,
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "_last_action": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAGjwfz+AshS+oHfePT9cQ7+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    }
+}

sac-BipedalWalkerHardcore-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d36c90341d386c04da282903350b41a97a8fd11d075ce3f785d1684b8bb4a81
+size 2656645

sac-BipedalWalkerHardcore-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc559dddb2e28fabff3a03abb4d0bebeecb78f66473f15c8953cdc407ffd53a
+size 747

sac-BipedalWalkerHardcore-v3/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 sha256:020c03b5fde8bfe9a7b66dc94610382214b53907607e9fd4097a65f3c36fe6ba
+size 278868