Initial commit

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,82 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **CartPole-v1**
+This is a trained model of a **PPO** 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
+
+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 CartPole-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env CartPole-v1  -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 CartPole-v1 -orga HumanCompatibleAI -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env CartPole-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env CartPole-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env CartPole-v1 -f logs/ -orga HumanCompatibleAI
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 256),
+             ('clip_range', 'lin_0.2'),
+             ('ent_coef', 0.0),
+             ('gae_lambda', 0.8),
+             ('gamma', 0.98),
+             ('learning_rate', 'lin_0.001'),
+             ('n_envs', 8),
+             ('n_epochs', 20),
+             ('n_steps', 32),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - cpu
+  - - env
+    - CartPole-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 0
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - gymnasium_models
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - 4
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2623485154
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,23 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 256
+  - - clip_range
+    - lin_0.2
+  - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.8
+  - - gamma
+    - 0.98
+  - - learning_rate
+    - lin_0.001
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 20
+  - - n_steps
+    - 32
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

ppo-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc70c310a4e48d5695193a20d481540ff2ace5ee7f7fa91283ed656c9a9460c
+size 139331

ppo-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.2.0a3

ppo-CartPole-v1/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7f7418355ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7418355f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f74182da040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f74182da0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f74182da160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f74182da1f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f74182da280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f74182da310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f74182da3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f74182da430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f74182da4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f74182da550>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f7418340c60>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 100096,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1695118822606160808,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0009600000000000719,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 7820,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "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]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "n_steps": 32,
+    "gamma": 0.98,
+    "gae_lambda": 0.8,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 256,
+    "n_epochs": 20,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

ppo-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5bbd8485411386d16f603d7183b06f0fc195c9a0f6e71574cefec19497656e4
+size 82425

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1332622cdd6d8b3d87122f5745c0d0fb2f0bb53f7001a32a2d15d968691f2fb
+size 40641

ppo-CartPole-v1/pytorch_variables.pth

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

ppo-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.4.0-156-generic-x86_64-with-glibc2.29 # 173-Ubuntu SMP Tue Jul 11 07:25:22 UTC 2023
+- Python: 3.8.10
+- Stable-Baselines3: 2.2.0a3
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.24.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb0b5edddbb6a9758f23d423afad69ca841be8d8bc63d287b01720155832f46
+size 54435

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T12:29:40.188261"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2618a2eca87839302b2418a9564368dd56e7c37edbbd56099fa713d7148cdb
+size 9515