Subiendo modelo para certificacion

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 269.10 +/- 18.22
+      value: 290.81 +/- 12.23
       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 0x7e3346764e00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e3346764ea0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e3346764f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e3346764fe0>", "_build": "<function ActorCriticPolicy._build at 0x7e3346765080>", "forward": "<function ActorCriticPolicy.forward at 0x7e3346765120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e33467651c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e3346765260>", "_predict": "<function ActorCriticPolicy._predict at 0x7e3346765300>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e33467653a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e3346765440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e33467654e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e33468a3440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1212416, "_total_timesteps": 1200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1767366309737099682, "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": -0.010346666666666726, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 592, "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:": "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", "__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 0x7e33468e1bc0>", "reset": "<function RolloutBuffer.reset at 0x7e33468e1c60>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7e33468e1d00>", "add": "<function RolloutBuffer.add at 0x7e33468e1e40>", "get": "<function RolloutBuffer.get at 0x7e33468e1ee0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7e33468e1f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e3346823980>"}, "rollout_buffer_kwargs": {}, "batch_size": 128, "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-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.1", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}
+{"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 0x7f3fa97bc720>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3fa97bc7c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3fa97bc860>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3fa97bc900>", "_build": "<function ActorCriticPolicy._build at 0x7f3fa97bc9a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3fa97bca40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3fa97bcae0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3fa97bcb80>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3fa97bcc20>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3fa97bccc0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3fa97bcd60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3fa97bce00>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3fab615b80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1767382026050547088, "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": 1656, "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 0x7f3fa9729580>", "reset": "<function RolloutBuffer.reset at 0x7f3fa9729620>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f3fa97296c0>", "add": "<function RolloutBuffer.add at 0x7f3fa9729800>", "get": "<function RolloutBuffer.get at 0x7f3fa97298a0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f3fa9729940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3fa9bbfd00>"}, "rollout_buffer_kwargs": {}, "batch_size": 128, "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, "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": 16, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.1", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff7d56ad9577c4ace0ea37d9b35ae614f52ee5ab02c232a694502f9ba04d2be
-size 149911
+oid sha256:ac9b597a81c340a72dce671b61a2ed5e9d3186b980a878e1225fb2aa5d75ef86
+size 150128

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7e3346764e00>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e3346764ea0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e3346764f40>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e3346764fe0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7e3346765080>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7e3346765120>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e33467651c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e3346765260>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7e3346765300>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e33467653a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e3346765440>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e33467654e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f3fa97bc720>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3fa97bc7c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3fa97bc860>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3fa97bc900>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f3fa97bc9a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f3fa97bca40>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3fa97bcae0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3fa97bcb80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f3fa97bcc20>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3fa97bccc0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3fa97bcd60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3fa97bce00>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7e33468a3440>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f3fab615b80>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1212416,
-    "_total_timesteps": 1200000,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1767366309737099682,
+    "start_time": 1767382026050547088,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdgIAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAIAAAAAAACATUA9+ciZPoWDcTzJrZ++rupJPfDhmDsAAAAAAAAAAPPSnr0c7Fg/FrC8PcU8374YQjO+RiI8PgAAAAAAAAAAMxsmPHANgj7q0mi+Ypm1vgZE0r08jca8AAAAAAAAAABmj9E9DKxCP7qbbr1kc7u+RFz7PdgMkb0AAAAAAAAAAFrXq72r168+Mi3BPkHReb5GXTM+WISwPQAAAAAAAAAAgH/+PXUnGj/I2Ry+yxzKvmPdeT162QC+AAAAAAAAAACa4/U8XLycP1P2Hj4Qqe++CqNZPCwtij0AAAAAAAAAANNsQz5zQHE/luE/PGFy0r46ylA+aSQOvQAAAAAAAAAATdlaPc9FXD/jmLc8jA3VvqC1Az3rd1K8AAAAAAAAAABmcMu8I8c3P++CKj5CEsW+53+AO+4l1D0AAAAAAAAAAACwajtb9K4/Uk62PWrU+r6s5ZE6FSwUPQAAAAAAAAAAzXIuPaTWOT4opge+TIqNvlcqzL09ryo6AAAAAAAAAADGWgU+1PH5PhJXU7501bK+x5zWu3SEGL4AAAAAAAAAADOx1zz4aJY9Fhb2vccZjr44/me9UeAqvQAAAAAAAAAA8LuAPtFtQj9EbiO+1bCWvoyxOT5+YP+9AAAAAAAAAACaLnY9KfNjPlLFfr6rf5u+ynzqvbJqEzwAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsIhpSMAUOUdJRSlC4="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,42 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.010346666666666726,
+    "_current_progress_remaining": -0.015808000000000044,
     "_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": 592,
-    "observation_space": {
-        ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "gAWVdwIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBNudW1weS5fY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoliAAAAAAAAAAAAAgwAAAIMAAACDBAAAgwdsPycAAACDBAAAAgAAAAICUaAtLCIWUjAFDlHSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolggAAAAAAAAAAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBZ0lFKUjARoaWdolGgTKJYgAAAAAAAAAAAAIEAAACBAAAAgQQAAIEHbD8lAAAAgQQAAgD8AAIA/lGgLSwiFlGgWdJRSlIwNYm91bmRlZF9hYm92ZZRoEyiWCAAAAAAAAAABAQEBAQEBAZRoHUsIhZRoFnSUUpSMCGxvd19yZXBylIxbWyAtMi41ICAgICAgICAtMi41ICAgICAgIC0xMC4gICAgICAgIC0xMC4gICAgICAgICAtNi4yODMxODU1IC0xMC4KICAtMC4gICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMU1sgMi41ICAgICAgICAyLjUgICAgICAgMTAuICAgICAgICAxMC4gICAgICAgICA2LjI4MzE4NTUgMTAuCiAgMS4gICAgICAgICAxLiAgICAgICBdlIwKX25wX3JhbmRvbZROdWIu",
-        "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu",
-        "dtype": "int64",
-        "n": "4",
-        "start": "0",
-        "_shape": [],
-        "_np_random": null
-    },
-    "n_envs": 16,
+    "_n_updates": 1656,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
@@ -89,14 +64,14 @@
         "__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 0x7e33468e1bc0>",
-        "reset": "<function RolloutBuffer.reset at 0x7e33468e1c60>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7e33468e1d00>",
-        "add": "<function RolloutBuffer.add at 0x7e33468e1e40>",
-        "get": "<function RolloutBuffer.get at 0x7e33468e1ee0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7e33468e1f80>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7f3fa9729580>",
+        "reset": "<function RolloutBuffer.reset at 0x7f3fa9729620>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f3fa97296c0>",
+        "add": "<function RolloutBuffer.add at 0x7f3fa9729800>",
+        "get": "<function RolloutBuffer.get at 0x7f3fa97298a0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f3fa9729940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7e3346823980>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f3fa9bbfd00>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 128,
@@ -109,6 +84,31 @@
     "clip_range_vf": null,
     "normalize_advantage": true,
     "target_kl": null,
+    "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": 16,
     "lr_schedule": {
         ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
         ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dfd10bf150d47705ad76b544d4e9f216fad7d6da539e006053e27cd63d3a87
-size 88695
+oid sha256:b294f03e1e1f5556071b3dce7a4dee788149cb50d6ac860904383ca82a04ef2a
+size 88887

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e818711c9834eefd40fc49df95dabcead90c6c920fe26d815a49467f4f3828
+oid sha256:2c39eee824dce96a5c326d8fc84c5307874dce92a1d455a9fbdda4d92fea19fc
 size 44095

results.json

@@ -1 +1 @@
-{"mean_reward": 269.10413605890665, "std_reward": 18.21979885480864, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-02T15:36:47.030573"}
+{"mean_reward": 290.80504439999993, "std_reward": 12.228973337825122, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-02T19:48:26.773490"}