Initial commit

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,80 @@
+---
+library_name: stable-baselines3
+tags:
+- InvertedPendulum-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: InvertedPendulum-v2
+      type: InvertedPendulum-v2
+    metrics:
+    - type: mean_reward
+      value: 11.20 +/- 0.98
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **InvertedPendulum-v2**
+This is a trained model of a **PPO** agent playing **InvertedPendulum-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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo ppo --env InvertedPendulum-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env InvertedPendulum-v2  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo ppo --env InvertedPendulum-v2 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env InvertedPendulum-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env InvertedPendulum-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env InvertedPendulum-v2 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 64),
+             ('clip_range', 0.4),
+             ('ent_coef', 1.37976e-07),
+             ('gae_lambda', 0.9),
+             ('gamma', 0.999),
+             ('learning_rate', 0.000222425),
+             ('max_grad_norm', 0.3),
+             ('n_envs', 1),
+             ('n_epochs', 5),
+             ('n_steps', 32),
+             ('n_timesteps', 1000000.0),
+             ('normalize', True),
+             ('policy', 'MlpPolicy'),
+             ('vf_coef', 0.19816),
+             ('normalize_kwargs', {'norm_obs': True, 'norm_reward': False})])
+```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - InvertedPendulum-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 115154852
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/InvertedPendulum-v2__ppo__115154852__1675807330
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,29 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 64
+  - - clip_range
+    - 0.4
+  - - ent_coef
+    - 1.37976e-07
+  - - gae_lambda
+    - 0.9
+  - - gamma
+    - 0.999
+  - - learning_rate
+    - 0.000222425
+  - - max_grad_norm
+    - 0.3
+  - - n_envs
+    - 1
+  - - n_epochs
+    - 5
+  - - n_steps
+    - 32
+  - - n_timesteps
+    - 1000000.0
+  - - normalize
+    - true
+  - - policy
+    - MlpPolicy
+  - - vf_coef
+    - 0.19816

env_kwargs.yml

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

ppo-InvertedPendulum-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f6953e7d5375b2fd7ed09bdd7827e125f410f0e8bfbc883a4e541989e3b4f0
+size 143150

ppo-InvertedPendulum-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

ppo-InvertedPendulum-v2/data

@@ -0,0 +1,103 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 0x7f9816812ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9816812f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9816814040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f98168140d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9816814160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f98168141f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9816814280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9816814310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f98168143a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9816814430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f98168144c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9816814550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f98168135c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float64",
+        "_shape": [
+            4
+        ],
+        "low": "[-inf -inf -inf -inf]",
+        "high": "[inf inf inf inf]",
+        "bounded_below": "[False False False False]",
+        "bounded_above": "[False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-3.]",
+        "high": "[3.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1675807333681879242,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/InvertedPendulum-v2__ppo__115154852__1675807330/InvertedPendulum-v2",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAFQDRArH83M/D1XxH1MEcL8xb7nw+uaDv1C+UWYq7n6/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwSGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 156250,
+    "n_steps": 32,
+    "gamma": 0.999,
+    "gae_lambda": 0.9,
+    "ent_coef": 1.37976e-07,
+    "vf_coef": 0.19816,
+    "max_grad_norm": 0.3,
+    "batch_size": 64,
+    "n_epochs": 5,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-InvertedPendulum-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b404e029c7e64a5ea5101cb7f50dc9d8b3997bd7cea7da63e6640c54c161b98a
+size 83184

ppo-InvertedPendulum-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f772f740d6e260a022d8f2802dc252535613d4a59ca8e84297f449e463dbbeb8
+size 40830

ppo-InvertedPendulum-v2/pytorch_variables.pth

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

ppo-InvertedPendulum-v2/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5d510ce6b60fa10ea5d3cace727a9fb00709e5b1a83562a1a6f6b42eba5a80
+size 133311

results.json

@@ -0,0 +1 @@
+{"mean_reward": 11.2, "std_reward": 0.9797958971132711, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T15:40:50.999257"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e63792418c264b446fb01e0b65e8008130aaf1d5b7d2be2ecb707c97e78d30
+size 467310

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b3d4467ac88c879345c3d28f0d56b5ee0c665fa4a2fe2f3ce1e4cf12140b3c
+size 4131