First submit for LunarLander-v2

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: 253.33 +/- 11.60
+      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 0x000001A66789D620>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001A66789D6C0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001A66789D760>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001A66789D800>", "_build": "<function ActorCriticPolicy._build at 0x000001A66789D8A0>", "forward": "<function ActorCriticPolicy.forward at 0x000001A66789D940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001A66789D9E0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001A66789DA80>", "_predict": "<function ActorCriticPolicy._predict at 0x000001A66789DB20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001A66789DBC0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001A66789DC60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001A66789DD00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001A66788F340>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1714152083282207300, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAODEfD58kDk/crnLPS+/8L7bxDE+yiBvvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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, "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": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.22631-SP0 10.0.22631", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cpu", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3474545f79663d7cc9ae93e10ff2dc8aa7e8d98ebca496b8fa69eb2f311fad1
+size 146683

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 0x000001A66789D620>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001A66789D6C0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001A66789D760>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001A66789D800>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001A66789D8A0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001A66789D940>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001A66789D9E0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001A66789DA80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001A66789DB20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001A66789DBC0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001A66789DC60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001A66789DD00>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000001A66788F340>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1714152083282207300,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAODEfD58kDk/crnLPS+/8L7bxDE+yiBvvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.00044800000000000395,
+    "_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": 3908,
+    "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,
+    "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": 1,
+    "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 sha256:0055c8970256be58e86b33f2ec09c701ff624f2c13e8fa5e88da22602f39255e
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c0a1b2c17a2e263d9a29735811f33e67aae13927c764ff47a3fb940881c8ab
+size 43634

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4dde0c1ad63b7740276006a06cc491b21b407ea6c889928c223ec77ddad79f
+size 864

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,8 @@
+- OS: Windows-10-10.0.22631-SP0 10.0.22631
+- Python: 3.11.9
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.3.0+cpu
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.28.1

results.json

@@ -0,0 +1 @@
+{"mean_reward": 253.329504, "std_reward": 11.604342314918053, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-27T02:53:52.503992"}