Upload PPO LunarLander-v2 trained agent

README.md

@@ -1,11 +1,10 @@
 ---
+library_name: stable-baselines3
 tags:
-- CartPole-v1
-- ppo
+- LunarLander-v2
 - deep-reinforcement-learning
 - reinforcement-learning
-- custom-implementation
-- deep-rl-course
+- stable-baselines3
 model-index:
 - name: PPO
   results:
@@ -13,49 +12,26 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 184.00 +/- 51.34
+      value: 283.16 +/- 16.88
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+# **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).
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+## Usage (with Stable-baselines3)
+TODO: Add your code
 
-  # Hyperparameters
-  ```python
-  {'exp_name': 'ppo-LunarLander-v2'
-'seed': 1
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'CartPole-v1'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'repo_id': 'nirmanpatel/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
-  ```
-  
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -1 +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 0x796e7ee61120>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x796e7ee611c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x796e7ee61260>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x796e7ee61300>", "_build": "<function ActorCriticPolicy._build at 0x796e7ee613a0>", "forward": "<function ActorCriticPolicy.forward at 0x796e7ee61440>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x796e7ee614e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x796e7ee61580>", "_predict": "<function ActorCriticPolicy._predict at 0x796e7ee61620>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x796e7ee616c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x796e7ee61760>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x796e7ee61800>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x796e7efd2e40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1782296898320097058, "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-6.6.122+-x86_64-with-glibc2.35 # 1 SMP Thu Apr 30 18:17:14 UTC 2026", "Python": "3.12.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.11.0+cu128", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 416, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7972cd69a020>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7972cd69a0c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7972cd69a160>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7972cd69a200>", "_build": "<function ActorCriticPolicy._build at 0x7972cd69a2a0>", "forward": "<function ActorCriticPolicy.forward at 0x7972cd69a340>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7972cd69a3e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7972cd69a480>", "_predict": "<function ActorCriticPolicy._predict at 0x7972cd69a520>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7972cd69a5c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7972cd69a660>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7972cd69a700>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7972cd7de740>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1507328, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1790972448293506407, "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": -0.004885333333333408, "_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": 618, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "high": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "low_repr": null, "high_repr": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__firstlineno__": 343, "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, it is only involved in policy and value function training but not action selection.\n\n:param buffer_size: Max number of element in the buffer\n:param observation_space: Observation space\n:param action_space: Action space\n:param device: PyTorch device\n:param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n    Equivalent to classic advantage when set to 1.\n:param gamma: Discount factor\n:param n_envs: Number of parallel environments\n", "__init__": "<function RolloutBuffer.__init__ at 0x7972cd606200>", "reset": "<function RolloutBuffer.reset at 0x7972cd6062a0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7972cd606340>", "add": "<function RolloutBuffer.add at 0x7972cd6063e0>", "get": "<function RolloutBuffer.get at 0x7972cd606480>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7972cd606520>", "__static_attributes__": ["actions", "advantages", "episode_starts", "full", "gae_lambda", "gamma", "generator_ready", "log_probs", "observations", "returns", "rewards", "values"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7972cd601080>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.122+-x86_64-with-glibc2.39 # 1 SMP Thu Apr 30 18:17:14 UTC 2026", "Python": "3.13.15", "Stable-Baselines3": "2.9.0", "PyTorch": "2.11.0+cu130", "GPU Enabled": "True", "Numpy": "2.1.3", "Cloudpickle": "3.1.2", "Gymnasium": "1.3.0", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b6787fdcde96d7a1871898b7d29c87a00dd687f682085fc8d2b98f7024221a
-size 149996
+oid sha256:f209f72086f50b1f2c3b63596399dfb01b1b47ac638b42c8e3cbeb3348bde34a
+size 150235

ppo-LunarLander-v3/_stable_baselines3_version

@@ -1 +1 @@
-2.8.0
+2.9.0

ppo-LunarLander-v3/data

@@ -3,58 +3,78 @@
         ":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 0x7cc9881ad760>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cc9881ad800>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cc9881ad8a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cc9881ad940>",
-        "_build": "<function ActorCriticPolicy._build at 0x7cc9881ad9e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7cc9881ada80>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cc9881adb20>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cc9881adbc0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7cc9881adc60>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cc9881add00>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cc9881adda0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cc9881ade40>",
+        "__firstlineno__": 416,
+        "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7972cd69a020>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7972cd69a0c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7972cd69a160>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7972cd69a200>",
+        "_build": "<function ActorCriticPolicy._build at 0x7972cd69a2a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7972cd69a340>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7972cd69a3e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7972cd69a480>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7972cd69a520>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7972cd69a5c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7972cd69a660>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7972cd69a700>",
+        "__static_attributes__": [
+            "action_dist",
+            "action_net",
+            "activation_fn",
+            "dist_kwargs",
+            "features_dim",
+            "features_extractor",
+            "log_std",
+            "log_std_init",
+            "mlp_extractor",
+            "net_arch",
+            "optimizer",
+            "ortho_init",
+            "pi_features_extractor",
+            "share_features_extractor",
+            "use_sde",
+            "value_net",
+            "vf_features_extractor"
+        ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cc9881c4040>"
+        "_abc_impl": "<_abc._abc_data object at 0x7972cd7de740>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 1507328,
+    "_total_timesteps": 1500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1776587847643506222,
+    "start_time": 1790972448293506407,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.004885333333333408,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 248,
+    "_n_updates": 618,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -63,13 +83,13 @@
         "bounded_below": "[ True  True  True  True  True  True  True  True]",
         "high": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]",
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
-        "low_repr": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]",
-        "high_repr": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]",
+        "low_repr": null,
+        "high_repr": null,
         "_np_random": null
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwVbnVtcHkuY29yZS5tdWx0aWFycmF5lIwGc2NhbGFylJOUaAtDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgRaAtDCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu",
         "dtype": "int64",
         "n": "4",
         "start": "0",
@@ -87,16 +107,31 @@
         ":type:": "<class 'abc.ABCMeta'>",
         ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=",
         "__module__": "stable_baselines3.common.buffers",
+        "__firstlineno__": 343,
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
-        "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x7cc988122520>",
-        "reset": "<function RolloutBuffer.reset at 0x7cc9881225c0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7cc988122660>",
-        "add": "<function RolloutBuffer.add at 0x7cc9881227a0>",
-        "get": "<function RolloutBuffer.get at 0x7cc988122840>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7cc9881228e0>",
+        "__doc__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, it is only involved in policy and value function training but not action selection.\n\n:param buffer_size: Max number of element in the buffer\n:param observation_space: Observation space\n:param action_space: Action space\n:param device: PyTorch device\n:param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n    Equivalent to classic advantage when set to 1.\n:param gamma: Discount factor\n:param n_envs: Number of parallel environments\n",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7972cd606200>",
+        "reset": "<function RolloutBuffer.reset at 0x7972cd6062a0>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7972cd606340>",
+        "add": "<function RolloutBuffer.add at 0x7972cd6063e0>",
+        "get": "<function RolloutBuffer.get at 0x7972cd606480>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7972cd606520>",
+        "__static_attributes__": [
+            "actions",
+            "advantages",
+            "episode_starts",
+            "full",
+            "gae_lambda",
+            "gamma",
+            "generator_ready",
+            "log_probs",
+            "observations",
+            "returns",
+            "rewards",
+            "values"
+        ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7cc9885b6380>"
+        "_abc_impl": "<_abc._abc_data object at 0x7972cd601080>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

ppo-LunarLander-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7cc1bfdafb5134be0ebf1f4c3d9dc0027a40376b6f84c87144ad3d0f2c9199
+oid sha256:ba39158601f85dfc8b5c7b3af97b2edf0ee98d2e98b3cb727ac4d661e94509e4
 size 88695

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988787b1c23674019a31785f7f3d556c599269e397fa05f8ed0e2c99fd15b7f9
+oid sha256:5a92c164c29b97eb846dcc1b953300b17dd6db434baed036aa28c03ff77361cf
 size 44095

ppo-LunarLander-v3/system_info.txt

@@ -1,9 +1,9 @@
-- OS: Linux-6.6.113+-x86_64-with-glibc2.35 # 1 SMP Mon Feb  2 12:27:57 UTC 2026
-- Python: 3.12.13
-- Stable-Baselines3: 2.8.0
-- PyTorch: 2.10.0+cu128
+- OS: Linux-6.6.122+-x86_64-with-glibc2.39 # 1 SMP Thu Apr 30 18:17:14 UTC 2026
+- Python: 3.13.15
+- Stable-Baselines3: 2.9.0
+- PyTorch: 2.11.0+cu130
 - GPU Enabled: True
-- Numpy: 1.26.4
+- Numpy: 2.1.3
 - Cloudpickle: 3.1.2
-- Gymnasium: 1.2.3
+- Gymnasium: 1.3.0
 - OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 184.0, "std_reward": 51.33809501724816, "n_evaluation_episodes": 10, "eval_datetime": "2026-10-02T19:33:41.342888"}
+{"mean_reward": 283.15598169488135, "std_reward": 16.878445066131903, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-02T20:55:54.966898"}