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 +1,64 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+# **TRPO** Agent playing **CartPole-v1**
+This is a trained model of a **TRPO** agent playing **CartPole-v1**
+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 CartPole-v1 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env CartPole-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env CartPole-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env CartPole-v1 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 512),
+             ('cg_damping', 0.001),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.99),
+             ('learning_rate', 0.001),
+             ('n_critic_updates', 20),
+             ('n_envs', 2),
+             ('n_steps', 512),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - CartPole-v1
+  - - 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
+    - 3580389388
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,21 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 512
+  - - cg_damping
+    - 0.001
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - 0.001
+  - - n_critic_updates
+    - 20
+  - - n_envs
+    - 2
+  - - n_steps
+    - 512
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e374dd360263248c5cdcc3b8a082a6238b44281d70c418ed68793699d01b2a5b
+size 57126

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:14:56.969574"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:768b7dbe5f02710699606302e5fb63ff9452fb06e813ca40706754491349e09e
+size 12970

trpo-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d07eac2007a94972074dd8e4a046cde985ba793bbcd8c8c6c27c28198fdea7
+size 97900

trpo-CartPole-v1/_stable_baselines3_version

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

trpo-CartPole-v1/data

@@ -0,0 +1,94 @@
+{
+    "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 0x7fb7c88f7950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb7c88f79e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb7c88f7a70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb7c88f7b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb7c88f7b90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb7c88f7c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb7c88f7cb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb7c88f7d40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb7c88f7dd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb7c88f7e60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb7c88f7ef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fb7c8949840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null,
+        "_shape": [
+            4
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 2,
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": []
+    },
+    "n_envs": 2,
+    "num_timesteps": 100352,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640704037.8940918,
+    "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": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 98,
+    "n_steps": 512,
+    "gamma": 0.99,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.0,
+    "vf_coef": 0.0,
+    "max_grad_norm": 0.0,
+    "normalize_advantage": true,
+    "batch_size": 512,
+    "cg_max_steps": 15,
+    "cg_damping": 0.001,
+    "line_search_shrinking_factor": 0.8,
+    "line_search_max_iter": 10,
+    "target_kl": 0.01,
+    "n_critic_updates": 20,
+    "sub_sampling_factor": 1
+}

trpo-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d1632d6d9344b91700c416c037a53bc3594fefbfd265252c0b505e40256331
+size 39681

trpo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206b0c87aaddca3e80b0555fcd5b4cd0bf749ccf75203fdf092f3a79839ec7c1
+size 40641

trpo-CartPole-v1/pytorch_variables.pth

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

trpo-CartPole-v1/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