Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

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: 265.75 +/- 16.37
+      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 0x7fa58b1c6670>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa58b1c6700>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa58b1c6790>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa58b1c6820>", "_build": "<function ActorCriticPolicy._build at 0x7fa58b1c68b0>", "forward": "<function ActorCriticPolicy.forward at 0x7fa58b1c6940>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa58b1c69d0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa58b1c6a60>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa58b1c6af0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa58b1c6b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa58b1c6c10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa58b1c6ca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa58b480b00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVeQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKE0AAU0AAWWMBmRldmljZZSMBGN1ZGGUjAJ2ZpRdlChNAAFNAAFldXUu", "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>", "net_arch": {"pi": [256, 256], "device": "cuda", "vf": [256, 256]}}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1761641122761606076, "learning_rate": 0.0003, "tensorboard_log": "./tensorboard_logs/ppo_lunarlander/", "_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": 248, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "n_epochs": 8, "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:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-153-generic-x86_64-with-glibc2.31 # 163-Ubuntu SMP Thu Aug 7 16:37:18 UTC 2025", "Python": "3.9.7", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.7.1+cu118", "GPU Enabled": "True", "Numpy": "1.26.3", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7929b227d86d1bf3ed0fcd766cfcdff4418ea953cb202af29c6e9984944ef01
+size 1682097

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,114 @@
+{
+    "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 0x7fa58b1c6670>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa58b1c6700>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa58b1c6790>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa58b1c6820>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa58b1c68b0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa58b1c6940>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa58b1c69d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa58b1c6a60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa58b1c6af0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa58b1c6b80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa58b1c6c10>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa58b1c6ca0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa58b480b00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVeQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKE0AAU0AAWWMBmRldmljZZSMBGN1ZGGUjAJ2ZpRdlChNAAFNAAFldXUu",
+        "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
+        "net_arch": {
+            "pi": [
+                256,
+                256
+            ],
+            "device": "cuda",
+            "vf": [
+                256,
+                256
+            ]
+        }
+    },
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1761641122761606076,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "./tensorboard_logs/ppo_lunarlander/",
+    "_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": 248,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 128,
+    "n_epochs": 8,
+    "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": 16,
+    "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 sha256:758c53f31b73fc83d568bcf55f013d602fc5eb336afd3d04a5a677d1cbeab27c
+size 1110391

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d10d04de94e99b54b2c778df7f393dc3ab8eeac6583376eca71ab6e2b9f206
+size 554879

ppo-LunarLander-v2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
+size 1261

ppo-LunarLander-v2/system_info.txt

@@ -0,0 +1,8 @@
+- OS: Linux-5.15.0-153-generic-x86_64-with-glibc2.31 # 163-Ubuntu SMP Thu Aug 7 16:37:18 UTC 2025
+- Python: 3.9.7
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.7.1+cu118
+- GPU Enabled: True
+- Numpy: 1.26.3
+- Cloudpickle: 3.1.1
+- Gymnasium: 0.28.1

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3562565249ac8997d3d7e7ed2c3a0a96376c37f9a1963663310ff5e5ce349f8
+size 173319

results.json

@@ -0,0 +1 @@
+{"mean_reward": 265.7466297863507, "std_reward": 16.37150280051783, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-28T17:58:07.421032"}