Upload PPO LunarLander-v3 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

@@ -16,16 +16,19 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 264.80 +/- 21.31
+      value: 265.66 +/- 25.54
       name: mean_reward
       verified: false
 ---
 
 # **PPO** Agent playing **LunarLander-v3**
+
 This is a trained model of a **PPO** agent playing **LunarLander-v3**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
+
 ## Usage (with Stable-baselines3)
+
 TODO: Add your code
 
 
@@ -34,4 +37,4 @@ 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", "__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 0x7d17e2044fe0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d17e2045080>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d17e2045120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d17e20451c0>", "_build": "<function ActorCriticPolicy._build at 0x7d17e2045260>", "forward": "<function ActorCriticPolicy.forward at 0x7d17e2045300>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d17e20453a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d17e2045440>", "_predict": "<function ActorCriticPolicy._predict at 0x7d17e20454e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d17e2045580>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d17e2045620>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d17e20456c0>", "__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 0x7d17e2517c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1791283373708929644, "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": 312, "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 0x7d17e21b51c0>", "reset": "<function RolloutBuffer.reset at 0x7d17e21b5260>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d17e21b5300>", "add": "<function RolloutBuffer.add at 0x7d17e21b53a0>", "get": "<function RolloutBuffer.get at 0x7d17e21b5440>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7d17e21b54e0>", "__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 0x7d17e21a1fc0>"}, "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"}}
+{"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 0x7b7071c89800>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b7071c898a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b7071c89940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b7071c899e0>", "_build": "<function ActorCriticPolicy._build at 0x7b7071c89a80>", "forward": "<function ActorCriticPolicy.forward at 0x7b7071c89b20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b7071c89bc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b7071c89c60>", "_predict": "<function ActorCriticPolicy._predict at 0x7b7071c89d00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b7071c89da0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b7071c89e40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b7071c89ee0>", "__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 0x7b7073d6a3c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1791286266735371483, "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", "_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 0x7b7071c019e0>", "reset": "<function RolloutBuffer.reset at 0x7b7071c01a80>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7b7071c01b20>", "add": "<function RolloutBuffer.add at 0x7b7071c01bc0>", "get": "<function RolloutBuffer.get at 0x7b7071c01c60>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7b7071c01d00>", "__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 0x7b7071dcc480>"}, "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 sha256:90da9dfde7d54f5d9a5366938c28260d8fb9904cb45f3fa110745c1db7daee29
-size 150319
+oid sha256:b5f325b0d35a6aaf706581354732e204a1480456cf5bde983e4d018e814f7890
+size 150343

ppo-LunarLander-v3/data

@@ -5,18 +5,18 @@
         "__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 0x7d17e2044fe0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d17e2045080>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d17e2045120>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d17e20451c0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7d17e2045260>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7d17e2045300>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d17e20453a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d17e2045440>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7d17e20454e0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d17e2045580>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d17e2045620>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d17e20456c0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b7071c89800>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b7071c898a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b7071c89940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b7071c899e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b7071c89a80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b7071c89b20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b7071c89bc0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b7071c89c60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b7071c89d00>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b7071c89da0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b7071c89e40>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b7071c89ee0>",
         "__static_attributes__": [
             "action_dist",
             "action_net",
@@ -37,7 +37,7 @@
             "vf_features_extractor"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d17e2517c40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b7073d6a3c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -46,12 +46,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1791283373708929644,
+    "start_time": 1791286266735371483,
     "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'>",
@@ -65,13 +65,13 @@
     "_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": 312,
+    "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -110,12 +110,12 @@
         "__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 0x7d17e21b51c0>",
-        "reset": "<function RolloutBuffer.reset at 0x7d17e21b5260>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d17e21b5300>",
-        "add": "<function RolloutBuffer.add at 0x7d17e21b53a0>",
-        "get": "<function RolloutBuffer.get at 0x7d17e21b5440>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7d17e21b54e0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7b7071c019e0>",
+        "reset": "<function RolloutBuffer.reset at 0x7b7071c01a80>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7b7071c01b20>",
+        "add": "<function RolloutBuffer.add at 0x7b7071c01bc0>",
+        "get": "<function RolloutBuffer.get at 0x7b7071c01c60>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7b7071c01d00>",
         "__static_attributes__": [
             "actions",
             "advantages",
@@ -131,7 +131,7 @@
             "values"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d17e21a1fc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b7071dcc480>"
     },
     "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:b8c800e27a4d47908e4570ccbb38107fdead4285428794451d5acf3f480e2f9e
+oid sha256:9ce90b895b9d21bf0134851843e8fe459045df998f66c7e2d7a97be9e670917c
 size 88695

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f866a9645027daae2b0334d23d094843c8d2ec444f46b1148a30311ea1fbeb7
+oid sha256:2ddcc516743268aa8ec915550a09d63f5f5bb25297490dbb2757c5b865045ceb
 size 44095

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02cefb595c9de5fee8b54a53f5e9501d8a45a2bb1ab7ec27e16dae4abf735ca
+size 160175

results.json

@@ -1 +1 @@
-{"mean_reward": 264.8019554, "std_reward": 21.314165667004982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-06T11:09:45.677812"}
+{"mean_reward": 265.6562451, "std_reward": 25.536109943626933, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-06T11:51:41.833957"}