Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 250.22 +/- 32.58
+      value: 268.26 +/- 21.36
       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 0x79be33507d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79be33507e20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79be33507ec0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79be33507f60>", "_build": "<function ActorCriticPolicy._build at 0x79be3350c040>", "forward": "<function ActorCriticPolicy.forward at 0x79be3350c0e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79be3350c180>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79be3350c220>", "_predict": "<function ActorCriticPolicy._predict at 0x79be3350c2c0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79be3350c360>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79be3350c400>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79be3350c4a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79be33508d00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1758313527326157871, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAADat5a9QALCP9g25b4KFPs9R72zvTuYh74AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////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", "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": 1, "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": "Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.8.0+cu128", "GPU Enabled": "True", "Numpy": "2.3.3", "Cloudpickle": "3.1.1", "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 0x78c7e2e6dc60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78c7e2e6dd00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78c7e2e6dda0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78c7e2e6de40>", "_build": "<function ActorCriticPolicy._build at 0x78c7e2e6dee0>", "forward": "<function ActorCriticPolicy.forward at 0x78c7e2e6df80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78c7e2e6e020>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78c7e2e6e0c0>", "_predict": "<function ActorCriticPolicy._predict at 0x78c7e2e6e160>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78c7e2e6e200>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78c7e2e6e2a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78c7e2e6e340>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78c7dffc3600>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1759179042284134126, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 248, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_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 0x78c7de6d8b80>", "reset": "<function RolloutBuffer.reset at 0x78c7de6d8c20>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x78c7de6d8cc0>", "add": "<function RolloutBuffer.add at 0x78c7de6d8e00>", "get": "<function RolloutBuffer.get at 0x78c7de6d8ea0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x78c7de6d8f40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78c7de851580>"}, "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-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.7.0", "PyTorch": "2.8.0+cu128", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43cb5080a02ff1dbe559f90f17afa4c6355bee8ab006ac5e5b0f4a9b77bc2324
-size 148868
+oid sha256:9545651fb755c60a102b774b238a7f33bc24348002b6a77f3b30be2a8c7722ff
+size 149948

ppo-LunarLander-v2/_stable_baselines3_version

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

ppo-LunarLander-v2/data

@@ -4,96 +4,114 @@
         ":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 0x79be33507d80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79be33507e20>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79be33507ec0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79be33507f60>",
-        "_build": "<function ActorCriticPolicy._build at 0x79be3350c040>",
-        "forward": "<function ActorCriticPolicy.forward at 0x79be3350c0e0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x79be3350c180>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79be3350c220>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x79be3350c2c0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79be3350c360>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79be3350c400>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x79be3350c4a0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x78c7e2e6dc60>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78c7e2e6dd00>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78c7e2e6dda0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78c7e2e6de40>",
+        "_build": "<function ActorCriticPolicy._build at 0x78c7e2e6dee0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78c7e2e6df80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78c7e2e6e020>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78c7e2e6e0c0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78c7e2e6e160>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78c7e2e6e200>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78c7e2e6e2a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78c7e2e6e340>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x79be33508d00>"
+        "_abc_impl": "<_abc._abc_data object at 0x78c7dffc3600>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1000448,
+    "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1758313527326157871,
+    "start_time": 1759179042284134126,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAADat5a9QALCP9g25b4KFPs9R72zvTuYh74AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.00044800000000000395,
+    "_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": 3908,
+    "_n_updates": 248,
     "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
+        "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
         "_np_random": null
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1,
+    "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 0x78c7de6d8b80>",
+        "reset": "<function RolloutBuffer.reset at 0x78c7de6d8c20>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x78c7de6d8cc0>",
+        "add": "<function RolloutBuffer.add at 0x78c7de6d8e00>",
+        "get": "<function RolloutBuffer.get at 0x78c7de6d8ea0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x78c7de6d8f40>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78c7de851580>"
+    },
+    "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 sha256:5279fa641fc3ab424499d44ea2b525df726506a3e05dc8b5d9a9d6aae4b85eaf
+oid sha256:6664155f5839328536ddc5995a654bae2fc9c26dc2acda6d3540db6beb7a731d
 size 88695

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d11e9366a89bd41204f470b13ada2c63c290192f07a11ea965e16b41121c741
+oid sha256:62b332f888aee4d13fd192eb98cf0539ecb001f1ee88c38f75f4aa14a2ac3544
 size 44095

ppo-LunarLander-v2/system_info.txt

@@ -1,8 +1,9 @@
 - OS: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025
 - Python: 3.11.13
-- Stable-Baselines3: 2.0.0a5
+- Stable-Baselines3: 2.7.0
 - PyTorch: 2.8.0+cu128
 - GPU Enabled: True
-- Numpy: 2.3.3
+- Numpy: 1.26.4
 - Cloudpickle: 3.1.1
-- Gymnasium: 0.28.1
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

results.json

@@ -1 +1 @@
-{"mean_reward": 250.2208326890218, "std_reward": 32.580554492928904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-19T17:17:59.350132"}
+{"mean_reward": 268.25581251695, "std_reward": 21.3644829760265, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-29T17:00:03.517379"}