Upload PPO LunarLander-v2 trained agent

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: 255.04 +/- 23.76
+      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 0x7ef53b1a1ab0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ef53b1a1b40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ef53b1a1bd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ef53b1a1c60>", "_build": "<function ActorCriticPolicy._build at 0x7ef53b1a1cf0>", "forward": "<function ActorCriticPolicy.forward at 0x7ef53b1a1d80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ef53b1a1e10>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ef53b1a1ea0>", "_predict": "<function ActorCriticPolicy._predict at 0x7ef53b1a1f30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ef53b1a1fc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ef53b1a2050>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ef53b1a20e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ef53b1134c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1735240198709888684, "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": -162.84, "_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": 337, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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:bacc9de980a6269d2d12166942f57db68d0be692166fa958403839c543b84c06
+size 145356

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 0x7ef53b1a1ab0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ef53b1a1b40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ef53b1a1bd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ef53b1a1c60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ef53b1a1cf0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ef53b1a1d80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ef53b1a1e10>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ef53b1a1ea0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ef53b1a1f30>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ef53b1a1fc0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ef53b1a2050>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ef53b1a20e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ef53b1134c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 16384,
+    "_total_timesteps": 100,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1735240198709888684,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAACb5Tz2xB26Dus3uRW35LM/GeG68kJaOAAAgD8AAIA/pvjoPVxfCroCsNY6wEkiOEhq9joqRHq5AAAAAAAAgD8AAPg57iugP3MaLDsURZG+BbvRPHgiIb0AAAAAAAAAAI3Oi700Dbc/AiBevgT9Zb4Oi/u9s0RWvgAAAAAAAAAAmpTaveoksD8oN4m+DKeSvjk/Qr4b1LG9AAAAAAAAAACmrBY+E8WIP1joSz5pl7S+2vEkPjrS+70AAAAAAAAAAJpEjryPXni6wopFuZWoHzY9BS+62bOPtQAAgD8AAIA/drGmvibUIj/eH2M+DqSIvpMEU73vOkU9AAAAAAAAAACzagU9Un6rP9C2ED5ZtIu+gFI0uQbAYD0AAAAAAAAAAOYgyz0tqj0+vmoEvmulf75VAO28s3tOvQAAAAAAAAAAAOjtPFwLf7rmxTW0ul2Mr5sSzboL1o4zAACAPwAAgD8z6wU71mqzPxa71zxT1zi+tH3UvO2cEL0AAAAAAAAAAABzlr32PDm6f6s5OzBghjb1OJc76gNcugAAgD8AAIA/QNzSPbj+jLkUNLc44GUMNBWhEjvKwde3AAAAAAAAgD/AU9c9e9KOutUFzjd+Z8ky9NAkugWB7rYAAAAAAACAPxpqCz5It0k/1ZxHPdcVdr6qV5w9CYcFvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+    },
+    "_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": -162.84,
+    "_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": 337,
+    "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "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:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+    }
+}

ppo-LunarLander-v2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc8a38baebe8411db550fd2dcea3e3940fd41d8f442f27947ba5461312365b
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8c814185936642e553e9d29ea1dc92a2ab794612ce8f4145308757a93e8788
+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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.5.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 255.03576620000004, "std_reward": 23.759061020256613, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-26T19:19:54.651282"}