Upload PPO LunarLander-v2 trained agent

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: stable-baselines3
 tags:
-- LunarLander-v2
+- LunarLander-v3
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
@@ -12,17 +12,17 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: LunarLander-v3
+      type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 255.67 +/- 24.12
+      value: 279.55 +/- 20.40
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
+# **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)

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 0x000001E7EDE33880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001E7EDE33910>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001E7EDE339A0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001E7EDE33A30>", "_build": "<function ActorCriticPolicy._build at 0x000001E7EDE33AC0>", "forward": "<function ActorCriticPolicy.forward at 0x000001E7EDE33B50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001E7EDE33BE0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001E7EDE33C70>", "_predict": "<function ActorCriticPolicy._predict at 0x000001E7EDE33D00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001E7EDE33D90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001E7EDE33E20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001E7EDE33EB0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001E7EDE34C40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1764406601264000700, "learning_rate": 0.0003, "tensorboard_log": "runs/ppo-LunarLander-v2", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_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": 492, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 8, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.26100-SP0 10.0.26100", "Python": "3.10.19", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "2.2.6", "Cloudpickle": "3.1.2", "Gymnasium": "0.28.1"}}
+{"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 0x000001FD95F40550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001FD95F405E0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001FD95F40670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001FD95F40700>", "_build": "<function ActorCriticPolicy._build at 0x000001FD95F40790>", "forward": "<function ActorCriticPolicy.forward at 0x000001FD95F40820>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001FD95F408B0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001FD95F40940>", "_predict": "<function ActorCriticPolicy._predict at 0x000001FD95F409D0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001FD95F40A60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001FD95F40AF0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001FD95F40B80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001FD95F365C0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1764502061030649900, "learning_rate": 0.0003, "tensorboard_log": "runs/ppo-LunarLander-v3", "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////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": 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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgIjAJpOJSJiIeUUpQoSwNoDE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaBFoFEMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMCl9ucF9yYW5kb22UTnViLg==", "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 0x000001FD95C97D00>", "reset": "<function RolloutBuffer.reset at 0x000001FD95C97D90>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x000001FD95C97E20>", "add": "<function RolloutBuffer.add at 0x000001FD95C97EB0>", "get": "<function RolloutBuffer.get at 0x000001FD95C97F40>", "_get_samples": "<function RolloutBuffer._get_samples at 0x000001FD95CB8040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001FD95CAA880>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Windows-10-10.0.26200-SP0 10.0.26200", "Python": "3.10.19", "Stable-Baselines3": "2.7.0", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "2.2.6", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c30c1976ce3e10b5139f239502af6b8cbc95c8b8764af51b791a8a7be9ecb04
-size 148501
+oid sha256:6a79f98e61518d970ef52481aeb6b8be5b17874dec296d91e68b438d6ff44c89
+size 149246

ppo-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-2.0.0a5
+2.7.0

ppo-LunarLander-v2/data

@@ -4,96 +4,111 @@
         ":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 0x000001E7EDE33880>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001E7EDE33910>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001E7EDE339A0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001E7EDE33A30>",
-        "_build": "<function ActorCriticPolicy._build at 0x000001E7EDE33AC0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x000001E7EDE33B50>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001E7EDE33BE0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001E7EDE33C70>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x000001E7EDE33D00>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001E7EDE33D90>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001E7EDE33E20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001E7EDE33EB0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000001FD95F40550>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000001FD95F405E0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000001FD95F40670>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000001FD95F40700>",
+        "_build": "<function ActorCriticPolicy._build at 0x000001FD95F40790>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000001FD95F40820>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000001FD95F408B0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000001FD95F40940>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000001FD95F409D0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000001FD95F40A60>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000001FD95F40AF0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000001FD95F40B80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x000001E7EDE34C40>"
+        "_abc_impl": "<_abc._abc_data object at 0x000001FD95F365C0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1007616,
+    "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1764406601264000700,
+    "start_time": 1764502061030649900,
     "learning_rate": 0.0003,
-    "tensorboard_log": "runs/ppo-LunarLander-v2",
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
-    },
+    "tensorboard_log": "runs/ppo-LunarLander-v3",
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVfAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpQu"
+        ":serialized:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAABAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.007616000000000067,
+    "_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": 492,
+    "_n_updates": 496,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
-        "bounded_below": "[ True  True  True  True  True  True  True  True]",
-        "bounded_above": "[ True  True  True  True  True  True  True  True]",
         "_shape": [
             8
         ],
-        "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
-        "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
-        "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]",
-        "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]",
+        "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgIjAJpOJSJiIeUUpQoSwNoDE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaBFoFEMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMCl9ucF9yYW5kb22UTnViLg==",
+        "dtype": "int64",
         "n": "4",
         "start": "0",
         "_shape": [],
-        "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 8,
+    "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 0x000001FD95C97D00>",
+        "reset": "<function RolloutBuffer.reset at 0x000001FD95C97D90>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x000001FD95C97E20>",
+        "add": "<function RolloutBuffer.add at 0x000001FD95C97EB0>",
+        "get": "<function RolloutBuffer.get at 0x000001FD95C97F40>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x000001FD95CB8040>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000001FD95CAA880>"
+    },
+    "rollout_buffer_kwargs": {},
     "batch_size": 64,
     "n_epochs": 4,
     "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":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 'function'>",
-        ":serialized:": "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"
+        ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
+        ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu",
+        "value_schedule": "ConstantSchedule(val=0.0003)"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:453684bca273b693d8ba2f23d34b5b46518ec8d711c474bd5676f2a9abc978f4
-size 88695
+oid sha256:c2a09d5d68d7fda1ce498062510d737822a34411ae6322b3ed239fb92656d687
+size 88887

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd23bf2b98c4759a45b0b213d5d582379c66e37eb17f7cb213cc3c766e0943b
+oid sha256:513c864f1565dbedf93b4d4a1e15d8c398d34beee941c1de2a6e4d6aed28dcc8
 size 44095

ppo-LunarLander-v2/system_info.txt

@@ -1,8 +1,8 @@
-- OS: Windows-10-10.0.26100-SP0 10.0.26100
+- OS: Windows-10-10.0.26200-SP0 10.0.26200
 - Python: 3.10.19
-- Stable-Baselines3: 2.0.0a5
+- Stable-Baselines3: 2.7.0
 - PyTorch: 2.9.1+cu128
 - GPU Enabled: True
 - Numpy: 2.2.6
 - Cloudpickle: 3.1.2
-- Gymnasium: 0.28.1
+- Gymnasium: 1.2.2

results.json

@@ -1 +1 @@
-{"mean_reward": 255.66715454610403, "std_reward": 24.116825540816393, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-29T17:07:13.055411"}
+{"mean_reward": 279.5547146483108, "std_reward": 20.403787454765574, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-30T19:49:05.469874"}