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

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 198.41 +/- 98.98
+      value: -838.04 +/- 428.35
       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 0x7a027aba7f60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a027abac040>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a027abac0e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a027abac180>", "_build": "<function ActorCriticPolicy._build at 0x7a027abac220>", "forward": "<function ActorCriticPolicy.forward at 0x7a027abac2c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a027abac360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a027abac400>", "_predict": "<function ActorCriticPolicy._predict at 0x7a027abac4a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a027abac540>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a027abac5e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a027abac680>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a027af21440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1756085142329798623, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABmQuI7j4ZKulYE3TvC1pC2evlaufW7jLUAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_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 0x7a027ab30d60>", "reset": "<function RolloutBuffer.reset at 0x7a027ab30e00>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7a027ab30ea0>", "add": "<function RolloutBuffer.add at 0x7a027ab30fe0>", "get": "<function RolloutBuffer.get at 0x7a027ab31080>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7a027ab31120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a027af6da80>"}, "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.12.11", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "1.2.0", "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 0x7efea8a5b7e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efea8a5b880>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efea8a5b920>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efea8a5b9c0>", "_build": "<function ActorCriticPolicy._build at 0x7efea8a5ba60>", "forward": "<function ActorCriticPolicy.forward at 0x7efea8a5bb00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efea8a5bba0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efea8a5bc40>", "_predict": "<function ActorCriticPolicy._predict at 0x7efea8a5bce0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efea8a5bd80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efea8a5be20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efea8a5bec0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efed774e7c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": "Generator(PCG64)"}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "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 0x7efea8bdc680>", "reset": "<function RolloutBuffer.reset at 0x7efea8bdc720>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7efea8bdc7c0>", "add": "<function RolloutBuffer.add at 0x7efea8bdc900>", "get": "<function RolloutBuffer.get at 0x7efea8bdc9a0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7efea8bdca40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efea8b9e940>"}, "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-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.12.11", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "1.2.0", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67f730ae2863ecd0432d2455c19cce83681b991c69fd5e7771b23a119951d76
-size 149902
+oid sha256:89d43c8ef24a354f82d661f8f3721d801c20d965d8670edf1e9d03c3a3c43924
+size 58447

ppo-LunarLander-v3/data

@@ -4,57 +4,45 @@
         ":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 0x7a027aba7f60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a027abac040>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a027abac0e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a027abac180>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a027abac220>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a027abac2c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a027abac360>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a027abac400>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a027abac4a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a027abac540>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a027abac5e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a027abac680>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7efea8a5b7e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efea8a5b880>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efea8a5b920>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efea8a5b9c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7efea8a5ba60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7efea8a5bb00>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efea8a5bba0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efea8a5bc40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7efea8a5bce0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efea8a5bd80>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efea8a5be20>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efea8a5bec0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a027af21440>"
+        "_abc_impl": "<_abc._abc_data object at 0x7efed774e7c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1000448,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1756085142329798623,
+    "start_time": 0.0,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAABmQuI7j4ZKulYE3TvC1pC2evlaufW7jLUAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.00044800000000000395,
+    "_current_progress_remaining": 1.0,
     "_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": 3908,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "gAWVGQQAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBNudW1weS5fY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoliAAAAAAAAAAAAAgwAAAIMAAACDBAAAgwdsPycAAACDBAAAAgAAAAICUaAtLCIWUjAFDlHSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolggAAAAAAAAAAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBZ0lFKUjARoaWdolGgTKJYgAAAAAAAAAAAAIEAAACBAAAAgQQAAIEHbD8lAAAAgQQAAgD8AAIA/lGgLSwiFlGgWdJRSlIwNYm91bmRlZF9hYm92ZZRoEyiWCAAAAAAAAAABAQEBAQEBAZRoHUsIhZRoFnSUUpSMCGxvd19yZXBylIxbWyAtMi41ICAgICAgICAtMi41ICAgICAgIC0xMC4gICAgICAgIC0xMC4gICAgICAgICAtNi4yODMxODU1IC0xMC4KICAtMC4gICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMU1sgMi41ICAgICAgICAyLjUgICAgICAgMTAuICAgICAgICAxMC4gICAgICAgICA2LjI4MzE4NTUgMTAuCiAgMS4gICAgICAgICAxLiAgICAgICBdlIwKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlGgyjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIwTbnVtcHkucmFuZG9tLl9wY2c2NJSMBVBDRzY0lJOUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaD+KEWGDF4PLIYab66YVc3CiRLUAjANpbmOUihDnqkDK6YT+OOKIzhBzIwAkdYwKaGFzX3VpbnQzMpRLAIwIdWludGVnZXKUSwB1jBpudW1weS5yYW5kb20uYml0X2dlbmVyYXRvcpSMG19fcHl4X3VucGlja2xlX1NlZWRTZXF1ZW5jZZSTlGhEjAxTZWVkU2VxdWVuY2WUk5RKIqLqA06HlFKUKIoQHVpUJAPGNKPSsNF82CJwZEsAaBMolhAAAAAAAAAAixiggRwHVo4W+vaD9mUUfpRoCIwCdTSUiYiHlFKUKEsDaAxOTk5K/////0r/////SwB0lGJLBIWUaBZ0lFKUSwQpdJRihpRihZRSlHViLg==",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -69,12 +57,12 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWVqgIAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlGgbjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIwTbnVtcHkucmFuZG9tLl9wY2c2NJSMBVBDRzY0lJOUhZRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaCiKEcYJb/qdAXuiweaVm6m4zrEAjANpbmOUihDZOfcaDjCiEZiqMZdKXT4IdYwKaGFzX3VpbnQzMpRLAYwIdWludGVnZXKUigWuH0aTAHWMGm51bXB5LnJhbmRvbS5iaXRfZ2VuZXJhdG9ylIwbX19weXhfdW5waWNrbGVfU2VlZFNlcXVlbmNllJOUaC2MDFNlZWRTZXF1ZW5jZZSTlEoiouoDToeUUpQoihE8UKS3sW3GB7I/eaiec5ngAEsAjBNudW1weS5fY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolhAAAAAAAAAAGSaocLt8CjIShP2O3zT+cJRoC4wCdTSUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGJLBIWUjAFDlHSUUpRLBCl0lGKGlGKFlFKUdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
-        "_np_random": null
+        "_np_random": "Generator(PCG64)"
     },
     "n_envs": 1,
     "n_steps": 1024,
@@ -89,14 +77,14 @@
         "__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 0x7a027ab30d60>",
-        "reset": "<function RolloutBuffer.reset at 0x7a027ab30e00>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7a027ab30ea0>",
-        "add": "<function RolloutBuffer.add at 0x7a027ab30fe0>",
-        "get": "<function RolloutBuffer.get at 0x7a027ab31080>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7a027ab31120>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7efea8bdc680>",
+        "reset": "<function RolloutBuffer.reset at 0x7efea8bdc720>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7efea8bdc7c0>",
+        "add": "<function RolloutBuffer.add at 0x7efea8bdc900>",
+        "get": "<function RolloutBuffer.get at 0x7efea8bdc9a0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7efea8bdca40>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a027af6da80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7efea8b9e940>"
     },
     "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 sha256:935d65b579e0da8cdcac91ab952e0d11bf755b645d6eee822b24c2209e7a2462
-size 88695
+oid sha256:f615de3a949886a7af5eecdd75a7a19b6a2709653ea7a923f94f772a765db224
+size 1581

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90e2d1bbd5777122351b9c79e4f59e0fe207c12ca6e0cbd213b0d6772b72801
+oid sha256:8c34e3637bfdfb6a417be38510137675c7afc7cae0832237ec6a37f5c4f19d5d
 size 44095

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f62a594e751b8563e22250e3cd71b34758972a984fadc72b00aacfbcc903c2
+size 152926

results.json

@@ -1 +1 @@
-{"mean_reward": 198.40954768919352, "std_reward": 98.98321951434875, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-25T02:10:36.651229"}
+{"mean_reward": -838.0437964388402, "std_reward": 428.35420579451693, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-25T02:15:49.661634"}