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:
+- HopperBulletEnv-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: HopperBulletEnv-v0
+      type: HopperBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 223.97 +/- 34.40
+      name: mean_reward
+      verified: false
+---
+
+# **SAC** Agent playing **HopperBulletEnv-v0**
+This is a trained model of a **SAC** agent playing **HopperBulletEnv-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 HopperBulletEnv-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env HopperBulletEnv-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 HopperBulletEnv-v0 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo sac --env HopperBulletEnv-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo sac --env HopperBulletEnv-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo sac --env HopperBulletEnv-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', 'lin_7.3e-4'),
+             ('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
+    - HopperBulletEnv-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
+    - 216112874
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/HopperBulletEnv-v0__sac__216112874__1671931837
+  - - 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
+    - lin_7.3e-4
+  - - 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 sha256:72b6f62456e5da4b7f9dae70fa1e23631bbfadc67ff9283c51805f5fc7cc2b19
+size 1350861

results.json

@@ -0,0 +1 @@
+{"mean_reward": 223.9651049, "std_reward": 34.39977342224693, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T15:14:45.599963"}

sac-HopperBulletEnv-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ddf4fa27cc645be78c6c02ef3be6151c075c1fbc1097b22a436f6c53d9726c
+size 5692681

sac-HopperBulletEnv-v0/_stable_baselines3_version

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

sac-HopperBulletEnv-v0/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cbb25ef89db596f02e6fb8c542ecb0b8dbf9e7f91d305b294821b8252859a7
+size 1033702

sac-HopperBulletEnv-v0/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:367db86fbf11170b6da430688133f0d76971ce9d59aa9d7ddf6f96e63d1f4aa4
+size 2060601

sac-HopperBulletEnv-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 0x7f2cf3dd2ca0>",
+        "_build": "<function SACPolicy._build at 0x7f2cf3dd2d30>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7f2cf3dd2dc0>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7f2cf3dd2e50>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7f2cf3dd2ee0>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7f2cf3dd2f70>",
+        "forward": "<function SACPolicy.forward at 0x7f2cf3dda040>",
+        "_predict": "<function SACPolicy._predict at 0x7f2cf3dda0d0>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7f2cf3dda160>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f2cf3dd6f40>"
+    },
+    "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": [
+            15
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf]",
+        "high": "[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]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -1.]",
+        "high": "[1. 1. 1.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ 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": 1671931839861077358,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVWwMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAksTQwh8AIgAFABTAJSMhAogICAgICAgIFByb2dyZXNzIHdpbGwgZGVjcmVhc2UgZnJvbSAxIChiZWdpbm5pbmcpIHRvIDAKICAgICAgICA6cGFyYW0gcHJvZ3Jlc3NfcmVtYWluaW5nOiAoZmxvYXQpCiAgICAgICAgOnJldHVybjogKGZsb2F0KQogICAgICAgIJSFlCmMEnByb2dyZXNzX3JlbWFpbmluZ5SFlIw0L2hvbWUvcWdhbGxvdWVkZWMvcmwtYmFzZWxpbmVzMy16b28vcmxfem9vMy91dGlscy5weZSMBGZ1bmOUTSIBQwIABpSMDWluaXRpYWxfdmFsdWWUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjAdybF96b28zlIwIX19uYW1lX1+UjA1ybF96b28zLnV0aWxzlIwIX19maWxlX1+UjDQvaG9tZS9xZ2FsbG91ZWRlYy9ybC1iYXNlbGluZXMzLXpvby9ybF96b28zL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgXaA6MDF9fcXVhbG5hbWVfX5SMHWxpbmVhcl9zY2hlZHVsZS48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UKIwScHJvZ3Jlc3NfcmVtYWluaW5nlIwIYnVpbHRpbnOUjAVmbG9hdJSTlIwGcmV0dXJulGgtdYwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UaAmMC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9H668QI2OyhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    },
+    "tensorboard_log": "runs/HopperBulletEnv-v0__sac__216112874__1671931837/HopperBulletEnv-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:": "gAWVsQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJY8AAAAAAAAAMq0FD4AAAAAAACAP3dgYz8AAAAAU5BKPgAAAAAnc6u+zOcLP/IvxL7g000/Vo89P+TIWb8m9jM/AAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsPhpSMAUOUdJRSlC4="
+    },
+    "_episode_num": 5338,
+    "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 0x7f2cf3e2a430>",
+        "add": "<function ReplayBuffer.add at 0x7f2cf3e2a4c0>",
+        "sample": "<function ReplayBuffer.sample at 0x7f2cf3e2a550>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f2cf3e2a5e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f2cf3e20d00>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLCGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -3.0,
+    "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:": "gAWVgQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYMAAAAAAAAAHSXxr4YvA4+gLS2PpSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsDhpSMAUOUdJRSlC4="
+    }
+}

sac-HopperBulletEnv-v0/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e194523c90fe7f57459ff5845156b9553377bb8dddfec17dc64ce5e395e2c62
+size 1507

sac-HopperBulletEnv-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68620c4ad86b6db64a9c051dbb72f0481772b1772a1388b06b26c3b6748a542
+size 2575624

sac-HopperBulletEnv-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254a506eedff4dd921841e727b145017a97b09d2da9a03bc99b3ccbc02a580c4
+size 747

sac-HopperBulletEnv-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:c74259ca0a9af672e54eff9df30534615206ac2aaa542a559142dac2bb8f0312
+size 146631