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 +1,62 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: TRPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -224.04 +/- 139.76
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+---
+
+# **TRPO** Agent playing **Pendulum-v1**
+This is a trained model of a **TRPO** agent playing **Pendulum-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 Pendulum-v1 -orga sb3 -f logs/
+python enjoy.py --algo trpo --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo trpo --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo trpo --env Pendulum-v1 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('gamma', 0.9),
+             ('n_critic_updates', 15),
+             ('n_envs', 2),
+             ('n_steps', 1024),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,65 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - trpo
+  - - env
+    - Pendulum-v0
+  - - 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
+    - 843550859
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1

config.yml

@@ -0,0 +1,17 @@
+!!python/object/apply:collections.OrderedDict
+- - - gamma
+    - 0.9
+  - - n_critic_updates
+    - 15
+  - - n_envs
+    - 2
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true

env_kwargs.yml

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

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e023a36e975bc1323fb41e923d005544165f31620a3db3c203b9c3d188734af
+size 116399

results.json

@@ -0,0 +1 @@
+{"mean_reward": -224.0432834, "std_reward": 139.76101055784463, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T13:04:15.114836"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb623c61a62908191ff84bdfe5bf9f1f97e5da6d6f3c72f77d72c91d55aeca80
+size 17884

trpo-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f19b1e71694eb10d8a344c65eff268a0c338d653c0c76862e1b1b7627d172ef
+size 97640

trpo-Pendulum-v1/_stable_baselines3_version

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

trpo-Pendulum-v1/data

@@ -0,0 +1,96 @@
+{
+    "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 0x7f6faf570950>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6faf5709e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6faf570a70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6faf570b00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f6faf570b90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f6faf570c20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6faf570cb0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f6faf570d40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6faf570dd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6faf570e60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6faf570ef0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f6faf5c1840>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gASVkQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMA2xvd5SMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlGgGjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwOFlGgKiUMMAACAvwAAgL8AAADBlHSUYowEaGlnaJRoEGgSSwCFlGgUh5RSlChLAUsDhZRoColDDAAAgD8AAIA/AAAAQZR0lGKMDWJvdW5kZWRfYmVsb3eUaBBoEksAhZRoFIeUUpQoSwFLA4WUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGKJQwMBAQGUdJRijA1ib3VuZGVkX2Fib3ZllGgQaBJLAIWUaBSHlFKUKEsBSwOFlGgoiUMDAQEBlHSUYowKX25wX3JhbmRvbZROjAZfc2hhcGWUSwOFlHViLg==",
+        "dtype": "float32",
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null,
+        "_shape": [
+            3
+        ]
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)",
+        "_shape": [
+            1
+        ]
+    },
+    "n_envs": 2,
+    "num_timesteps": 100352,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1640703832.6538694,
+    "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": null,
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": 4,
+    "_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": 49,
+    "n_steps": 1024,
+    "gamma": 0.9,
+    "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": 15,
+    "sub_sampling_factor": 1
+}

trpo-Pendulum-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c117bc27065a28ec4a81ec2d79ff47af3e9a2d3dfffa4ab36c1ba932bc699344
+size 39169

trpo-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4f0c347f59157e5b1ca94971d88b0a9f21380b14f63532b0c16aa28291d38b
+size 40382

trpo-Pendulum-v1/pytorch_variables.pth

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

trpo-Pendulum-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