First step in learning RL with HF!

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 267.30 +/- 18.57
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"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 0x7f93741d3e20>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f93741d3eb0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f93741d3f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f93741dc040>", "_build": "<function ActorCriticPolicy._build at 0x7f93741dc0d0>", "forward": "<function ActorCriticPolicy.forward at 0x7f93741dc160>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f93741dc1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f93741dc280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f93741dc310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f93741dc3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f93741dc430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f93741dc4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f93741d5600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1685135871540805870, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "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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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af746ecf65b954cb245f74cb9256c500381e7852138f801d549ea14cad5d5b3
+size 146755

ppo-LunarLander-v2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2/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 0x7f93741d3e20>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f93741d3eb0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f93741d3f40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f93741dc040>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f93741dc0d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f93741dc160>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f93741dc1f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f93741dc280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f93741dc310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f93741dc3a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f93741dc430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f93741dc4c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f93741d5600>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1685135871540805870,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_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": 248,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
+        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "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-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a00139ae2b2f452016dbbbc636b8f6ab6b4c70071aa3abceaddc7f8b2dff900
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c874f7300a8845242b668e63dad92e5cbda5fb5e35b4aa4657b02db93bec326b
+size 43329

ppo-LunarLander-v2/pytorch_variables.pth

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

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 267.29539606590964, "std_reward": 18.568863772882505, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-26T21:46:26.143710"}