My Second model on HuggingFace. And first lunarlander. Yay

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: 276.20 +/- 23.07
+      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 0x7fc888d31900>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc888d31990>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc888d31a20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc888d31ab0>", "_build": "<function ActorCriticPolicy._build at 0x7fc888d31b40>", "forward": "<function ActorCriticPolicy.forward at 0x7fc888d31bd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc888d31c60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc888d31cf0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fc888d31d80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc888d31e10>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc888d31ea0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc888d31f30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc888ecda00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705772404340165193, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_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": 310, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.001, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "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 sha256:50c962ac15fb69a9f724c465eab8e772f76ffc4ebcab5a9409c272e893531c5b
+size 147201

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,96 @@
+{
+    "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 0x7fc888d31900>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fc888d31990>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fc888d31a20>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fc888d31ab0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fc888d31b40>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fc888d31bd0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fc888d31c60>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fc888d31cf0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fc888d31d80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fc888d31e10>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fc888d31ea0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fc888d31f30>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fc888ecda00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1705772404340165193,
+    "learning_rate": 0.001,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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": 310,
+    "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.001,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "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 sha256:723f7d7a595e73c5373fe77e4af34e717c67827a80516e8ac290e6f18abdaf6a
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3200a2e805293de4b58eedce1cf3d4263d0fe8b48a989b6a95b8196c7c69653b
+size 43762

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 276.2015524115749, "std_reward": 23.069780629260052, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-20T21:15:07.405886"}