feat: Uploaded PPO LunarLander-v3 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,16 +16,19 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 256.79 +/- 29.50
+      value: 275.75 +/- 15.23
       name: mean_reward
       verified: false
 ---
 
 # **PPO** Agent playing **LunarLander-v3**
+
 This is a trained model of a **PPO** agent playing **LunarLander-v3**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
+
 ## Usage (with Stable-baselines3)
+
 TODO: Add your code
 
 
@@ -34,4 +37,4 @@ from stable_baselines3 import ...
 from huggingface_sb3 import load_from_hub
 
 ...
-```
+```

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__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 0x7d28b1d045e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d28b1d04680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d28b1d04720>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d28b1d047c0>", "_build": "<function ActorCriticPolicy._build at 0x7d28b1d04860>", "forward": "<function ActorCriticPolicy.forward at 0x7d28b1d04900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d28b1d049a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d28b1d04a40>", "_predict": "<function ActorCriticPolicy._predict at 0x7d28b1d04ae0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d28b1d04b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d28b1d04c20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d28b1d04cc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d28b1e4b280>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1045504, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1772025571147348560, "learning_rate": 0.0001, "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": -0.04550399999999999, "_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": 320, "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": 4084, "gamma": 0.999, "gae_lambda": 0.99, "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 0x7d28b1e81300>", "reset": "<function RolloutBuffer.reset at 0x7d28b1e813a0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d28b1e81440>", "add": "<function RolloutBuffer.add at 0x7d28b1e81580>", "get": "<function RolloutBuffer.get at 0x7d28b1e81620>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7d28b1e816c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d28b1f41300>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 20, "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/Gjbi6xxDLXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0001)"}, "system_info": {"OS": "Linux-6.6.113+-x86_64-with-glibc2.35 # 1 SMP Mon Feb  2 12:27:57 UTC 2026", "Python": "3.12.12", "Stable-Baselines3": "2.7.1", "PyTorch": "2.10.0+cu128", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.3", "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 0x795d316ee700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795d316ee7a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795d316ee840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795d316ee8e0>", "_build": "<function ActorCriticPolicy._build at 0x795d316ee980>", "forward": "<function ActorCriticPolicy.forward at 0x795d316eea20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795d316eeac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795d316eeb60>", "_predict": "<function ActorCriticPolicy._predict at 0x795d316eec00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795d316eeca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795d316eed40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795d316eede0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x795d316e61c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1772031617707628998, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_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": 496, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwVbnVtcHkuY29yZS5tdWx0aWFycmF5lIwGc2NhbGFylJOUaAtDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgRaAtDCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.99, "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 0x795d3165f560>", "reset": "<function RolloutBuffer.reset at 0x795d3165f600>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x795d3165f6a0>", "add": "<function RolloutBuffer.add at 0x795d3165f7e0>", "get": "<function RolloutBuffer.get at 0x795d3165f880>", "_get_samples": "<function RolloutBuffer._get_samples at 0x795d3165f920>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x795d317f7b40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.113+-x86_64-with-glibc2.35 # 1 SMP Mon Feb  2 12:27:57 UTC 2026", "Python": "3.12.12", "Stable-Baselines3": "2.7.1", "PyTorch": "2.10.0+cu128", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.3", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771272a62a47d7ad9e19f47c62fad29e757a8d0a8350a23de2237df0e6f1c766
-size 149999
+oid sha256:80b0d73e3109aea20a733f8c93d0ac859fe7f8e8797ef769a90be40b3049c5ac
+size 149912

ppo-LunarLander-v3/data

@@ -4,57 +4,57 @@
         ":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 0x7d28b1d045e0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d28b1d04680>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d28b1d04720>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d28b1d047c0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7d28b1d04860>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7d28b1d04900>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d28b1d049a0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d28b1d04a40>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7d28b1d04ae0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d28b1d04b80>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d28b1d04c20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d28b1d04cc0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x795d316ee700>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795d316ee7a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795d316ee840>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795d316ee8e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x795d316ee980>",
+        "forward": "<function ActorCriticPolicy.forward at 0x795d316eea20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x795d316eeac0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795d316eeb60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x795d316eec00>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795d316eeca0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795d316eed40>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x795d316eede0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d28b1e4b280>"
+        "_abc_impl": "<_abc._abc_data object at 0x795d316e61c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1045504,
+    "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1772025571147348560,
-    "learning_rate": 0.0001,
+    "start_time": 1772031617707628998,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAABAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.04550399999999999,
+    "_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": 320,
+    "_n_updates": 496,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -69,7 +69,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwVbnVtcHkuY29yZS5tdWx0aWFycmF5lIwGc2NhbGFylJOUaAtDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgRaAtDCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjApfbnBfcmFuZG9tlE51Yi4=",
         "dtype": "int64",
         "n": "4",
         "start": "0",
@@ -77,7 +77,7 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 4084,
+    "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.99,
     "ent_coef": 0.01,
@@ -89,18 +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 0x7d28b1e81300>",
-        "reset": "<function RolloutBuffer.reset at 0x7d28b1e813a0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7d28b1e81440>",
-        "add": "<function RolloutBuffer.add at 0x7d28b1e81580>",
-        "get": "<function RolloutBuffer.get at 0x7d28b1e81620>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7d28b1e816c0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x795d3165f560>",
+        "reset": "<function RolloutBuffer.reset at 0x795d3165f600>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x795d3165f6a0>",
+        "add": "<function RolloutBuffer.add at 0x795d3165f7e0>",
+        "get": "<function RolloutBuffer.get at 0x795d3165f880>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x795d3165f920>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d28b1f41300>"
+        "_abc_impl": "<_abc._abc_data object at 0x795d317f7b40>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,
-    "n_epochs": 20,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
         ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu",
@@ -111,7 +111,7 @@
     "target_kl": null,
     "lr_schedule": {
         ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
-        ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/Gjbi6xxDLXNic2Iu",
-        "value_schedule": "ConstantSchedule(val=0.0001)"
+        ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu",
+        "value_schedule": "ConstantSchedule(val=0.0003)"
     }
 }

ppo-LunarLander-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d15658500eccf3790330c8bd02786a455543361974c0925f6603a84eb0b67e9d
+oid sha256:e28af5ae7c1989a2d57cb8396a4bed2345b4efcfe4c4977e1a7ab4336a84d682
 size 88695

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca39a01687135996e032dc6a5d0992811fa1e30aa58ea8d1524be42f84c9c3c5
+oid sha256:daa8bbcb28beab7bd10f82920ed4f1e39b4d42687aca2d7ae614a5cb78ba8404
 size 44095

ppo-LunarLander-v3/system_info.txt

@@ -3,7 +3,7 @@
 - Stable-Baselines3: 2.7.1
 - PyTorch: 2.10.0+cu128
 - GPU Enabled: True
-- Numpy: 2.0.2
+- Numpy: 1.26.4
 - Cloudpickle: 3.1.2
 - Gymnasium: 1.2.3
 - OpenAI Gym: 0.25.2

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e54bd88277d54d476443b97ff8ede70eec1a964223cff5f7edf97f174a7628
+size 160297

results.json

@@ -1 +1 @@
-{"mean_reward": 256.7922645, "std_reward": 29.50244340698145, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-25T14:27:24.271886"}
+{"mean_reward": 275.75006659999997, "std_reward": 15.233774306606376, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-02-25T15:16:55.593909"}