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 +1,66 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLanderContinuous-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: SAC
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 251.89 +/- 71.75
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLanderContinuous-v2
+      type: LunarLanderContinuous-v2
+---
+
+# **SAC** Agent playing **LunarLanderContinuous-v2**
+This is a trained model of a **SAC** agent playing **LunarLanderContinuous-v2**
+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 LunarLanderContinuous-v2 -orga sb3 -f logs/
+python enjoy.py --algo sac --env LunarLanderContinuous-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo sac --env LunarLanderContinuous-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo sac --env LunarLanderContinuous-v2 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('buffer_size', 1000000),
+             ('ent_coef', 'auto'),
+             ('gamma', 0.99),
+             ('gradient_steps', 1),
+             ('learning_rate', 'lin_7.3e-4'),
+             ('learning_starts', 10000),
+             ('n_timesteps', 500000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[400, 300])'),
+             ('tau', 0.01),
+             ('train_freq', 1),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,59 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - sac
+  - - env
+    - LunarLanderContinuous-v2
+  - - 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
+    - 2927467908
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - buffer_size
+    - 1000000
+  - - ent_coef
+    - auto
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 1
+  - - learning_rate
+    - lin_7.3e-4
+  - - learning_starts
+    - 10000
+  - - n_timesteps
+    - 500000.0
+  - - 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 sha256:5641f0d5f6ae5e536f20c8def3687f1a896c5b6e55fb26890552f0bd6ac014f5
+size 172210

results.json

@@ -0,0 +1 @@
+{"mean_reward": 251.8879946, "std_reward": 71.7456622645129, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T18:54:11.860490"}

sac-LunarLanderContinuous-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb85183c6137ad5917b937310401f53cc7c17b17bee3995a015cb6492c2d4c4
+size 5546321

sac-LunarLanderContinuous-v2/_stable_baselines3_version

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

sac-LunarLanderContinuous-v2/actor.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6153cf84694da42091b40f4b1effa6947063869bebcc765d2cbbb9ea6e5c75b6
+size 1005173

sac-LunarLanderContinuous-v2/critic.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b475523df6c3b72947372a3a1e7e524b962cd1169533f7183543c206ed7dec
+size 2006429

sac-LunarLanderContinuous-v2/data

@@ -0,0 +1,121 @@
+{
+    "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 0x7fc068d62710>",
+        "_build": "<function SACPolicy._build at 0x7fc068d627a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fc068d62830>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fc068d628c0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fc068d62950>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fc068d629e0>",
+        "forward": "<function SACPolicy.forward at 0x7fc068d62a70>",
+        "_predict": "<function SACPolicy._predict at 0x7fc068d62b00>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fc068d62b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc068d44ab0>"
+    },
+    "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",
+        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False False]",
+        "bounded_above": "[False False False False False False False False]",
+        "_np_random": null,
+        "_shape": [
+            8
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-1. -1.]",
+        "high": "[1. 1.]",
+        "bounded_below": "[ True  True]",
+        "bounded_above": "[ True  True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            2
+        ]
+    },
+    "n_envs": 1,
+    "num_timesteps": 170117,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1614859433.51721,
+    "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:": "gASVqgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMgGs25vXvmmLoWYRy6mooOtSTVjLmFrTQ5AAAAAAAAgD+UdJRiLg=="
+    },
+    "_episode_num": 628,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.6597660000000001,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 160116,
+    "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:": "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 0x7fc0691c4b90>",
+        "add": "<function ReplayBuffer.add at 0x7fc0691c4c20>",
+        "sample": "<function ReplayBuffer.sample at 0x7fc068d287a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fc068d28830>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fc06921b5d0>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gASVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "target_entropy": -2.0,
+    "ent_coef": "auto",
+    "target_update_interval": 1,
+    "_last_dones": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "remove_time_limit_termination": false
+}

sac-LunarLanderContinuous-v2/ent_coef_optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe2ff0bc75ef6100141764b9174629c785ab1a39c8c34dc476cdb1ac3df650d
+size 1255

sac-LunarLanderContinuous-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8038c855862503f0bab074440f45af460fa8de6e39970c80392654ffde17c407
+size 2511109

sac-LunarLanderContinuous-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcfcacffe3cc75a55449e790987f3b000ded3b67e882c5fc5fd84b498f5e9ca
+size 747

sac-LunarLanderContinuous-v2/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:dd5d3e3f9cb9b62a2ba4afab1f47a1b6689d659498c132b495bb758c48907fbe
+size 20775