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: 252.22 +/- 18.04
+      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 0x7810e1a8c5e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7810e1a8c680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7810e1a8c720>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7810e1a8c7c0>", "_build": "<function ActorCriticPolicy._build at 0x7810e1a8c860>", "forward": "<function ActorCriticPolicy.forward at 0x7810e1a8c900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7810e1a8c9a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7810e1a8ca40>", "_predict": "<function ActorCriticPolicy._predict at 0x7810e1a8cae0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7810e1a8cb80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7810e1a8cc20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7810e1a8ccc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7810e1be20c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1750705430133291998, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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, "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": 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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2-qwstein.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab78c00fb740963a1ce388c1ae55196f4895ed2ae6a501fbe994411b4664a668
+size 148128

ppo-LunarLander-v2-qwstein/_stable_baselines3_version

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

ppo-LunarLander-v2-qwstein/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 0x7810e1a8c5e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7810e1a8c680>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7810e1a8c720>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7810e1a8c7c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7810e1a8c860>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7810e1a8c900>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7810e1a8c9a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7810e1a8ca40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7810e1a8cae0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7810e1a8cb80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7810e1a8cc20>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7810e1a8ccc0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7810e1be20c0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1750705430133291998,
+    "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+    },
+    "_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,
+    "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": 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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"
+    }
+}

ppo-LunarLander-v2-qwstein/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f6fc9fce3094dbdb2b513fe23dda45cc1a1bdd39a07f1b844799fcc7810a3a
+size 88362

ppo-LunarLander-v2-qwstein/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048e0ab22bdccb5803d563ea94d2a49dff28e04dfb65f342ed58da79ad6d5b32
+size 43762

ppo-LunarLander-v2-qwstein/pytorch_variables.pth

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

ppo-LunarLander-v2-qwstein/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025
+- Python: 3.11.13
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.6.0+cu124
+- 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 sha256:196cdcfa62b16c51bb69c8e2b3a265e23a7264432dc49a7e8308f885a25c43ab
+size 147290

results.json

@@ -0,0 +1 @@
+{"mean_reward": 252.22393409999995, "std_reward": 18.041501730690904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-23T19:58:44.493853"}