Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 265.99 +/- 15.11
+      value: 274.89 +/- 21.02
       name: mean_reward
       verified: false
 ---

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 0x0000024727561000>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000024727561090>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000024727561120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000247275611B0>", "_build": "<function ActorCriticPolicy._build at 0x0000024727561240>", "forward": "<function ActorCriticPolicy.forward at 0x00000247275612D0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000024727561360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000247275613F0>", "_predict": "<function ActorCriticPolicy._predict at 0x0000024727561480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000024727561510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000247275615A0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000024727561630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000024725936FC0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 983040, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1765197643773741900, "learning_rate": 0.0003, "tensorboard_log": "./runs/ppo-LunarLander-v3/", "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.021055999999999964, "_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": 956, "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": "[ -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.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgIjAJpOJSJiIeUUpQoSwNoDE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaBFoFEMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMCl9ucF9yYW5kb22UTnViLg==", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 4, "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", "__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 0x00000247272E4820>", "reset": "<function RolloutBuffer.reset at 0x00000247272E48B0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000247272E4940>", "add": "<function RolloutBuffer.add at 0x00000247272E49D0>", "get": "<function RolloutBuffer.get at 0x00000247272E4A60>", "_get_samples": "<function RolloutBuffer._get_samples at 0x00000247272E4AF0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000247272D23C0>"}, "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": "Windows-10-10.0.26200-SP0 10.0.26200", "Python": "3.10.19", "Stable-Baselines3": "2.7.0", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "2.2.6", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2"}}
+{"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 0x0000012303D5AC00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000012303D5ACA0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000012303D5AD40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000012303D5ADE0>", "_build": "<function ActorCriticPolicy._build at 0x0000012303D5AE80>", "forward": "<function ActorCriticPolicy.forward at 0x0000012303D5AF20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000012303D5AFC0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000012303D5B060>", "_predict": "<function ActorCriticPolicy._predict at 0x0000012303D5B100>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000012303D5B1A0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000012303D5B240>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000012303D5B2E0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000012303D5D400>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 310000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1769006084749650300, "learning_rate": 0.0003, "tensorboard_log": "./logs/tensorboard/", "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAACaYdq70pu0P2rQLL//LnY7q0X9O26UHD4AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.690752, "_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": 2416, "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": "[ -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.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgIjAJpOJSJiIeUUpQoSwNoDE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaBFoFEMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMCl9ucF9yYW5kb22UTnViLg==", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 1, "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", "__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 0x00000123039EC680>", "reset": "<function RolloutBuffer.reset at 0x00000123039EC720>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000123039EC7C0>", "add": "<function RolloutBuffer.add at 0x00000123039EC900>", "get": "<function RolloutBuffer.get at 0x00000123039EC9A0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x00000123039ECA40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000012303978F40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 8, "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": "Windows-10-10.0.26200-SP0 10.0.26200", "Python": "3.11.14", "Stable-Baselines3": "2.7.1", "PyTorch": "2.9.1+cu126", "GPU Enabled": "True", "Numpy": "2.3.5", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.3"}}

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3d36f2cb5014971f3367dcfa5c3f9c1a62abcdc59e5b1c77d3d67cfd04c644
-size 149338
+oid sha256:59ef99e742e0fb2202da687182a739178c1c54e75b4a1170cc4c776ab37713f6
+size 149503

ppo-LunarLander-v3/_stable_baselines3_version

@@ -1 +1 @@
-2.7.0
+2.7.1

ppo-LunarLander-v3/data

@@ -4,51 +4,54 @@
         ":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 0x0000024727561000>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000024727561090>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000024727561120>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000247275611B0>",
-        "_build": "<function ActorCriticPolicy._build at 0x0000024727561240>",
-        "forward": "<function ActorCriticPolicy.forward at 0x00000247275612D0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000024727561360>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000247275613F0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x0000024727561480>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000024727561510>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000247275615A0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000024727561630>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x0000012303D5AC00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000012303D5ACA0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000012303D5AD40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000012303D5ADE0>",
+        "_build": "<function ActorCriticPolicy._build at 0x0000012303D5AE80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x0000012303D5AF20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000012303D5AFC0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000012303D5B060>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x0000012303D5B100>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000012303D5B1A0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000012303D5B240>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000012303D5B2E0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x0000024725936FC0>"
+        "_abc_impl": "<_abc._abc_data object at 0x0000012303D5D400>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 983040,
+    "num_timesteps": 310000,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1765197643773741900,
+    "start_time": 1769006084749650300,
     "learning_rate": 0.0003,
-    "tensorboard_log": "./runs/ppo-LunarLander-v3/",
+    "tensorboard_log": "./logs/tensorboard/",
     "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAACaYdq70pu0P2rQLL//LnY7q0X9O26UHD4AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
     },
-    "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.021055999999999964,
+    "_current_progress_remaining": 0.690752,
     "_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": 956,
+    "_n_updates": 2416,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -73,7 +76,7 @@
         "_shape": [],
         "_np_random": null
     },
-    "n_envs": 4,
+    "n_envs": 1,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
@@ -86,18 +89,18 @@
         "__module__": "stable_baselines3.common.buffers",
         "__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 0x00000247272E4820>",
-        "reset": "<function RolloutBuffer.reset at 0x00000247272E48B0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000247272E4940>",
-        "add": "<function RolloutBuffer.add at 0x00000247272E49D0>",
-        "get": "<function RolloutBuffer.get at 0x00000247272E4A60>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x00000247272E4AF0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x00000123039EC680>",
+        "reset": "<function RolloutBuffer.reset at 0x00000123039EC720>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x00000123039EC7C0>",
+        "add": "<function RolloutBuffer.add at 0x00000123039EC900>",
+        "get": "<function RolloutBuffer.get at 0x00000123039EC9A0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x00000123039ECA40>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x00000247272D23C0>"
+        "_abc_impl": "<_abc._abc_data object at 0x0000012303978F40>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,
-    "n_epochs": 4,
+    "n_epochs": 8,
     "clip_range": {
         ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
         ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu",

ppo-LunarLander-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93dcd73917d6cb99f9dea74c94f43038f78cb7f4a78dc25d28cc79d9d5605d27
+oid sha256:dbd32face99281a6f8f4fbf1a9d47ab7ccaa3a1f0c3b4307d88ba43d1aba86e7
 size 88887

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd1f9f564cba5ee42233f80ee9a158e4ef3340fd19ac2baafe6ad0b89bf2b94
+oid sha256:8a7ed38de7099c9b27749a274c6ed44de53ceb4ec0cdc4c862bd0716fe4913ce
 size 44095

ppo-LunarLander-v3/system_info.txt

@@ -1,8 +1,8 @@
 - OS: Windows-10-10.0.26200-SP0 10.0.26200
-- Python: 3.10.19
-- Stable-Baselines3: 2.7.0
-- PyTorch: 2.9.1+cu128
+- Python: 3.11.14
+- Stable-Baselines3: 2.7.1
+- PyTorch: 2.9.1+cu126
 - GPU Enabled: True
-- Numpy: 2.2.6
+- Numpy: 2.3.5
 - Cloudpickle: 3.1.2
-- Gymnasium: 1.2.2
+- Gymnasium: 1.2.3

results.json

@@ -1 +1 @@
-{"mean_reward": 265.9860526717768, "std_reward": 15.105332893011974, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-08T20:57:32.758340"}
+{"mean_reward": 274.888229, "std_reward": 21.01577210789499, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-22T16:44:01.205795"}

vec_normalize.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5731353223eadcc3d39c3f5cec60f114006730cdb036be024388bb231a9d9fed
+size 1845