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 araffin -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 araffin -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 araffin
+```
+
+## 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
+    - 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
+  - - progress
+    - true
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 532292511
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - ''
+  - - track
+    - false
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 0
+  - - 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 sha256:83c55054d908ec2592d008671ee5dba834ecf4e0cd95ab9daf590b116710b6d8
+size 139276

ppo-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

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 0x7fb21ab22c20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fb21ab22cb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fb21ab22d40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fb21ab22dd0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fb21ab22e60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fb21ab22ef0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fb21ab22f80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fb21ab23010>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fb21ab230a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fb21ab23130>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fb21ab231c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fb21ab23250>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fb21ab14c00>"
+    },
+    "verbose": 0,
+    "policy_kwargs": {},
+    "num_timesteps": 52736,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1692303699326410655,
+    "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": 0.47263999999999995,
+    "_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": 4112,
+    "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:": "gAWVpQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlIwFUENHNjSUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaCiKEONhlaa3XlgJLUWWWTS1oRqMA2luY5SKEKlzeES8M4FYghr3OtvajUF1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpRLAHVidWIu",
+        "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 sha256:3b3231e1395daacc5e73510e7867cc8bfe387d40025594c723cf66823d29cfeb
+size 82425

ppo-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6c15ac92fac7483a369f550957bc05131ecab99349fb9e0eb2238d08f79d72
+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-5.15.0-78-generic-x86_64-with-glibc2.35 # 85-Ubuntu SMP Fri Jul 7 15:25:09 UTC 2023
+- Python: 3.10.9
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.1.0.dev20230420+cpu
+- GPU Enabled: False
+- Numpy: 1.23.0
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.29.0
+- OpenAI Gym: 0.26.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3733450166b03e25ae26f120e8aa709612db5937afa388963f9361885322aac
+size 53956

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-17T22:24:02.976798"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:436d7609cce400aba604a73323364ac7af347b23648ccfb40837411b5d557844
+size 7665