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: 270.50 +/- 13.87
+      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 0x782011b15d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x782011b15e10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x782011b15ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x782011b15f30>", "_build": "<function ActorCriticPolicy._build at 0x782011b15fc0>", "forward": "<function ActorCriticPolicy.forward at 0x782011b16050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x782011b160e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x782011b16170>", "_predict": "<function ActorCriticPolicy._predict at 0x782011b16200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x782011b16290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x782011b16320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x782011b163b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x782019b123c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701925253340146308, "learning_rate": 0.0003, "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": 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": 5, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo_lunar.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e88e450a97951dd7164164da1d9c70760bc054fc6be1497db6278b0bfebd5d
+size 147303

ppo_lunar/_stable_baselines3_version

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

ppo_lunar/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 0x782011b15d80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x782011b15e10>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x782011b15ea0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x782011b15f30>",
+        "_build": "<function ActorCriticPolicy._build at 0x782011b15fc0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x782011b16050>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x782011b160e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x782011b16170>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x782011b16200>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x782011b16290>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x782011b16320>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x782011b163b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x782019b123c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1701925253340146308,
+    "learning_rate": 0.0003,
+    "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": 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": 5,
+    "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_lunar/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9fce52f22a56ebb9c1d0e67c92df3a4c1ee8e1568248e193fdc734a737ac37
+size 88490

ppo_lunar/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93559115e1fbcaabf2ab18808c26a0ec303fd8ccd3dbea7ec8886c3638ecb3ae
+size 43762

ppo_lunar/pytorch_variables.pth

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

ppo_lunar/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu118
+- 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": 270.4957361719589, "std_reward": 13.872145689200496, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T06:14:13.142669"}