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 +1,60 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLanderContinuous-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 273.95 +/- 23.86
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLanderContinuous-v2
+      type: LunarLanderContinuous-v2
+---
+
+# **TRPO** Agent playing **LunarLanderContinuous-v2**
+This is a trained model of a **TRPO** 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 trpo --env LunarLanderContinuous-v2 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env LunarLanderContinuous-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env LunarLanderContinuous-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env LunarLanderContinuous-v2 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('n_critic_updates', 20),
+             ('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 200000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - LunarLanderContinuous-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - 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
+    - 3017201014
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,13 @@
+!!python/object/apply:collections.OrderedDict
+- - - n_critic_updates
+    - 20
+  - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 200000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250b5ec84b813b24df117ac318a8694f202eba7b2bb9f2c6022028bd50d55c58
+size 176664

results.json

@@ -0,0 +1 @@
+{"mean_reward": 273.95071140000005, "std_reward": 23.85809691936957, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:11:38.369033"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601818df2b766f2fde6fbbc3b542bfcbcfe42b94c22ac162fd5678f4c12ba1cb
+size 12267

trpo-LunarLanderContinuous-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30316eb2c7a5722751d6082404719febcbdd2a3ed5778f5555f4dc38986dfe75
+size 103491

trpo-LunarLanderContinuous-v2/_stable_baselines3_version

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

trpo-LunarLanderContinuous-v2/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7fa4d026e950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa4d026e9e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa4d026ea70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa4d026eb00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa4d026eb90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa4d026ec20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa4d026ecb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa4d026ed40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa4d026edd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa4d026ee60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa4d026eef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fa4d02bf840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "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": 2,
+    "num_timesteps": 110000,
+    "_total_timesteps": 200000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640769097.64864,
+    "learning_rate": 0.001,
+    "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:": "gASVygAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwJLCIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUNAAIhjOwiftD8nC7Q+vUoFPLuag7tZIaO9AAAAAAAAAAAAUMO6mB+0P+eSGr6KqSi+kjbjOqANDD0AAAAAAAAAAJR0lGIu"
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.45728,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 53,
+    "n_steps": 1024,
+    "gamma": 0.99,
+    "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": 15,
+    "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-LunarLanderContinuous-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62fe3127a0232f99d2dd5f3acf0548dd1a397f59ef5b1903f3e05ce758df0bc
+size 41729

trpo-LunarLanderContinuous-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ee55ebf76e0acdacf57625f939c9411a31cc0f8e4f5c991f40265eec447003
+size 43006

trpo-LunarLanderContinuous-v2/pytorch_variables.pth

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

trpo-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

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad9680b87af48851d3a43b36419309d59d542c6a849ddcdeb1315cbfd586552
+size 4534