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 +1,77 @@
+---
+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 qgallouedec -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 qgallouedec -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 qgallouedec
+```
+
+## 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)])
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - CartPole-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 5
+  - - eval_freq
+    - 25000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - 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
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 3048649980
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - /tmp/stable-baselines/
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - sb3

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 @@
+{}

ppo-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cc301ab474fcd2197d274c66171508210b235fc146cdebb0a73991d7e5b5c5
+size 142748

ppo-CartPole-v1/_stable_baselines3_version

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

ppo-CartPole-v1/data

@@ -0,0 +1,95 @@
+{
+    "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 0x7fcbd5c50d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fcbd5c50dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fcbd5c50e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fcbd5c50ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fcbd5c50f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fcbd5c51040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fcbd5c510d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fcbd5c51160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fcbd5c511f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fcbd5c51280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fcbd5c51310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fcbd5c513a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fcbd613f040>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_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]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 100096,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1660075777.2585804,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "/tmp/stable-baselines/CartPole-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_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,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQH9AAAAAAACMAWyUTfQBjAF0lEdARycVFhG6PXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEdATW5H3Dh1fZQoaAZHQH9AAAAAAABoB030AWgIR0BHQc0tRNypdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASSUVHnU2DXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEpEW8AaNuN1fZQoaAZHQH9AAAAAAABoB030AWgIR0BKWglF+d9VdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASlu1WsA/93V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEpfWn0kGA11fZQoaAZHQH9AAAAAAABoB030AWgIR0BKX0ojOcDsdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASnZtxdY4hnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEp3qk/KQq91fZQoaAZHQH9AAAAAAABoB030AWgIR0BKrM+3Ytg8dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS+IbGWD6FnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEvmlTm4iHJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BL6Hjp9qk/dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS/6fWcz68HV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEv+j2SMcZN1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMBVAZ88cNdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATBmrhisnzHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExR3oLXtjV1fZQoaAZHQH9AAAAAAABoB030AWgIR0BNeJHy3CsPdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATY4udwvQGHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQE2PzK9wm3R1fZQoaAZHQH9AAAAAAABoB030AWgIR0BNk2a+evpydX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATZNWS2Yv4HV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQE2rFVktmL91fZQoaAZHQH9AAAAAAABoB030AWgIR0BNrBQm/nGLdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATeLH0btJF3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQE8gI9C/oJR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BPJNSAH3UQdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATzgYekpI+XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQE87mxMWXTp1fZQoaAZHQH9AAAAAAABoB030AWgIR0BPO4smOU+tdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAT1eECeVcEHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQE9Y3WFvhqF1fZQoaAZHQH9AAAAAAABoB030AWgIR0BPkh6Skj5cdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUFf1uivgWXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFBixDst03h1fZQoaAZHQH9AAAAAAABoB030AWgIR0BQY6XfIjnndX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUG4lyBClanV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFBuHTZxrBV1fZQoaAZHQH9AAAAAAABoB030AWgIR0BQcYBikO7QdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUHH/DLr5ZnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFCYFqSHM2Z1fZQoaAZHQH9AAAAAAABoB030AWgIR0BRKoSpR4yHdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUTXMmnfl63V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFE2tUXHim51fZQoaAZHQH9AAAAAAABoB030AWgIR0BROFoHs1KodX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUThRrJr+HnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFFEjJdSl311fZQoaAZHQH9AAAAAAABoB030AWgIR0BRRTibUgB+dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUWIcjqv/znV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFK8QO4G2Th1fZQoaAZHQH9AAAAAAABoB030AWgIR0BSvpxFRYRvdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUr9tvXK8tnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFLKUlAu7H11fZQoaAZHQH9AAAAAAABoB030AWgIR0BSykoa1kUcdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAUtfqxC6YmnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFLYqLCN0eV1fZQoaAZHQH9AAAAAAABoB030AWgIR0BS9FiWmgrZdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAU4LiPyTY/XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFORfra/RE51fZQoaAZHQH9AAAAAAABoB030AWgIR0BTkoEGJN0vdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAU5SDVYp2EHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFOUesPrfLt1fZQoaAZHQH9AAAAAAABoB030AWgIR0BToRQN0/4ZdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAU6GVB2OhkHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFPGKJEYwZh1fZQoaAZHQH9AAAAAAABoB030AWgIR0BUU7N8ma6SdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVF5hqj8DS3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFRfQrtmcvx1fZQoaAZHQH9AAAAAAABoB030AWgIR0BUYNLDhtLtdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVGDKHO8kEHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFRsLlV94NZ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BUbLidat9ydX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVIYYdhiLEXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFUZQ+2VmjF1fZQoaAZHQH9AAAAAAABoB030AWgIR0BVG7HlwLmZdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVRxftx+8XnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFUm4ffXPJJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BVJtmlImPYdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVSnq6e5Fw3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFUy4EOiFkB1fZQoaAZHQH9AAAAAAABoB030AWgIR0BVS86FM7EHdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVdVSqEOAiHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFXgUfxMFll1fZQoaAZHQH9AAAAAAABoB030AWgIR0BV4Tifg75mdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVeLu/k/8mHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFXi5mh/RVp1fZQoaAZHQH9AAAAAAABoB030AWgIR0BV7whStNi6dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVe+KCQLeAXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFYJSydFvyd1fZQoaAZHQH9AAAAAAABoB030AWgIR0BWm+zyBkI5dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVp43CKrJbXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFandsi0OVh1fZQoaAZHQH9AAAAAAABoB030AWgIR0BWqSDqW1MNdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVqkYR/ViF3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQFa0WrOqvNh1fZQoaAZHQH9AAAAAAABoB030AWgIR0BWtMf7rLQpdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAVs3L2YfGMnVlLg=="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 7820,
+    "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
+}

ppo-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a182361b2ea0fd673499e033d8c53e8b84361c4efe722076f055380202e8c5
+size 82937

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3fecffabe6f4fe67aa50e860e6256259d61f4b91701cb6a5324b7abad88952b
+size 40769

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 +1,7 @@
+- 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:fa17707a9a44e8bf2bf19adb0ba4531c90a1681a8311fdd6eed3aebae54cbad8
+size 59183

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:19:23.770219"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd978cfb9c2de211ec342357b21b186657cf6599342c4b7757482ed35f1aabfd
+size 9482