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: 267.39 +/- 20.27
+      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 0x7c85bd192f80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c85bd193010>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c85bd1930a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c85bd193130>", "_build": "<function ActorCriticPolicy._build at 0x7c85bd1931c0>", "forward": "<function ActorCriticPolicy.forward at 0x7c85bd193250>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c85bd1932e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c85bd193370>", "_predict": "<function ActorCriticPolicy._predict at 0x7c85bd193400>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c85bd193490>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c85bd193520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c85bd1935b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c85bd136040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 13248, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1700331693055548422, "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": 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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": 0.0, "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-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-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada913a6b305f8f3e6630bee4da748d422b14c3ba91cd72c306194fe8fa15e82
+size 146043

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 0x7c85bd192f80>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c85bd193010>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c85bd1930a0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c85bd193130>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c85bd1931c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c85bd193250>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c85bd1932e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c85bd193370>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c85bd193400>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c85bd193490>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c85bd193520>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c85bd1935b0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7c85bd136040>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 13248,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1700331693055548422,
+    "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": 310,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
+        "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": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "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:accdb663e789d395c28e06b604a9c141acafed3aa102f84cd0329fa5aa727ea1
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa513b1811516d4a718aa3c455a3647b46e1ee68efb1850bbe692f297a73649
+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-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": 267.38685449999997, "std_reward": 20.269646437080418, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-18T18:25:20.009664"}