Upload PPO LunarLander-v2 trained agent v2.

.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: 279.73 +/- 19.60
+      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 0x7f9a101a1ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9a101a1f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9a101a2020>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9a101a20c0>", "_build": "<function ActorCriticPolicy._build at 0x7f9a101a2160>", "forward": "<function ActorCriticPolicy.forward at 0x7f9a101a2200>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9a101a22a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9a101a2340>", "_predict": "<function ActorCriticPolicy._predict at 0x7f9a101a23e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9a101a2480>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9a101a2520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9a101a25c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f9a1049bc00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVbAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoTQABTQABZYwCdmaUXZQoTQABTQABZXVhdS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [{"pi": [256, 256], "vf": [256, 256]}]}, "num_timesteps": 1515520, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1759093028093806320, "learning_rate": 0.0003, "tensorboard_log": "runs/v207pfip", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWViAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWFAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLFIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.010346666666666726, "_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": 740, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 20, "n_steps": 1024, "gamma": 0.995, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "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-6.6.97+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Sep  6 09:54:41 UTC 2025", "Python": "3.12.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.8.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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:fa66331692a4bc680719c740799750ab46b62f8e319c5dccbbc5c8cbd699d584
+size 1682080

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -0,0 +1,115 @@
+{
+    "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 0x7f9a101a1ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f9a101a1f80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f9a101a2020>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f9a101a20c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f9a101a2160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f9a101a2200>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f9a101a22a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f9a101a2340>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f9a101a23e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f9a101a2480>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f9a101a2520>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9a101a25c0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f9a1049bc00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVbAAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlH2UKIwCcGmUXZQoTQABTQABZYwCdmaUXZQoTQABTQABZXVhdS4=",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            {
+                "pi": [
+                    256,
+                    256
+                ],
+                "vf": [
+                    256,
+                    256
+                ]
+            }
+        ]
+    },
+    "num_timesteps": 1515520,
+    "_total_timesteps": 1500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1759093028093806320,
+    "learning_rate": 0.0003,
+    "tensorboard_log": "runs/v207pfip",
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWViAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWFAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLFIWUjAFDlHSUUpQu"
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.010346666666666726,
+    "_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": 740,
+    "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 20,
+    "n_steps": 1024,
+    "gamma": 0.995,
+    "gae_lambda": 0.9,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 256,
+    "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:f9c7f6d42a1da7abefb736e88087889f9040d7a1d7d93e1953e08b8e9ae95585
+size 1110199

ppo-LunarLander-v2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16dd911e0c9997ae452213c397b519f83a8b1a2e23b99413aa0e6f30b2f24c95
+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 +1,9 @@
+- OS: Linux-6.6.97+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Sep  6 09:54:41 UTC 2025
+- Python: 3.12.11
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.8.0+cu126
+- GPU Enabled: True
+- Numpy: 2.0.2
+- Cloudpickle: 3.1.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7be34d6049886385df511b21612f5578767cd6fa055a1eb5d2e943987e65cc
+size 151911

results.json

@@ -0,0 +1 @@
+{"mean_reward": 279.7267493, "std_reward": 19.599405570848926, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-28T21:36:20.008961"}