Initial commit

.gitattributes

@@ -25,3 +25,5 @@ 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
+vec_normalize.pkl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+library_name: stable-baselines3
+tags:
+- Swimmer-v3
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 365.53 +/- 1.57
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Swimmer-v3
+      type: Swimmer-v3
+---
+
+# **TRPO** Agent playing **Swimmer-v3**
+This is a trained model of a **TRPO** agent playing **Swimmer-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
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo trpo --env Swimmer-v3 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env Swimmer-v3  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env Swimmer-v3 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env Swimmer-v3 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('cg_damping', 0.1),
+             ('cg_max_steps', 25),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.9999),
+             ('learning_rate', 0.001),
+             ('n_critic_updates', 20),
+             ('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('sub_sampling_factor', 1),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - Swimmer-v3
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 50000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - 10
+  - - n_eval_envs
+    - 10
+  - - n_evaluations
+    - 20
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 10
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3578176095
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - cg_damping
+    - 0.1
+  - - cg_max_steps
+    - 25
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.9999
+  - - learning_rate
+    - 0.001
+  - - n_critic_updates
+    - 20
+  - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - sub_sampling_factor
+    - 1

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb48b28b8d85947e63c2a8e1e955521ac573786d9e47428aaa2c5c48b77b583
+size 1444896

results.json

@@ -0,0 +1 @@
+{"mean_reward": 365.5272635, "std_reward": 1.5657982544289208, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T12:59:38.904672"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e315e5802fb446f158236ba7090a74fa5f963bfa257854116d1fc716bedbc95e
+size 35782

trpo-Swimmer-v3.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c381dbc7e4db47dbe7d8fc5f446f8a61f32eaf41777116aec4c1f78cbb2bc94
+size 104762

trpo-Swimmer-v3/_stable_baselines3_version

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

trpo-Swimmer-v3/data

@@ -0,0 +1,102 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__module__": "stable_baselines3.common.policies",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\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 full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\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()`` 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 squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fcd61e03950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcd61e039e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcd61e03a70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcd61e03b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcd61e03b90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcd61e03c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcd61e03cb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcd61e03d40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcd61e03dd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcd61e03e60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcd61e03ef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fcd61e54840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "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": 2,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640686241.1886032,
+    "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": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVigAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwKFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAgAAlHSUYi4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVCgEAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwJLCIaUaAOMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUOAgGc2qscofT8K14FHGeaqv4zk491Av7M/DIekAddHoz/g51I8LL2vPzcKZKn6VrO/D8i73BIZtL/aAnWkr8axvxjOJHf+Abg/LAJ9Clk8oD+EbZnLjNGiv3DOyL9ufYi/XfWgNoMktr+odSTbriuuP2iIPcnq75I/AOYYTryMXT+UdJRiLg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0014719999999999178,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 489,
+    "n_steps": 1024,
+    "gamma": 0.9999,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.0,
+    "max_grad_norm": 0.0,
+    "normalize_advantage": true,
+    "batch_size": 128,
+    "cg_max_steps": 25,
+    "cg_damping": 0.1,
+    "line_search_shrinking_factor": 0.8,
+    "line_search_max_iter": 10,
+    "target_kl": 0.01,
+    "n_critic_updates": 20,
+    "sub_sampling_factor": 1
+}

trpo-Swimmer-v3/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bc73d6fcc45d904ba08026e212f7601d70936d09c42bfebb89ab4b98d18325
+size 41729

trpo-Swimmer-v3/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbc17ababd91d9d0ea9687e125e756372d504abc3c3c45b59978f5b70ddd163
+size 43006

trpo-Swimmer-v3/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

trpo-Swimmer-v3/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

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7057fad8e0259c0034703295a1b28a7126a9a4a40c65d53dad78c1d858190a
+size 4662