Lesgo!

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 250.99 +/- 65.46
+      value: 275.32 +/- 15.61
       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 0x7f638e4e8e00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f638e4e8ea0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f638e4e8f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f638e4e8fe0>", "_build": "<function ActorCriticPolicy._build at 0x7f638e4e9080>", "forward": "<function ActorCriticPolicy.forward at 0x7f638e4e9120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f638e4e91c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f638e4e9260>", "_predict": "<function ActorCriticPolicy._predict at 0x7f638e4e9300>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f638e4e93a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f638e4e9440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f638e4e94e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f638e4d7f00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2007040, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1749810538809862586, "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:": "gAWViAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWFAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLFIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_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": 392, "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, "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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 20, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.0-37-amd64-x86_64-with-glibc2.36 # 1 SMP PREEMPT_DYNAMIC Debian 6.1.140-1 (2025-05-22)", "Python": "3.11.2", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.7.1+cu126", "GPU Enabled": "True", "Numpy": "2.3.0", "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 0x7f77c0ee8e00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f77c0ee8ea0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f77c0ee8f40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77c0ee8fe0>", "_build": "<function ActorCriticPolicy._build at 0x7f77c0ee9080>", "forward": "<function ActorCriticPolicy.forward at 0x7f77c0ee9120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f77c0ee91c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f77c0ee9260>", "_predict": "<function ActorCriticPolicy._predict at 0x7f77c0ee9300>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77c0ee93a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f77c0ee9440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77c0ee94e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f77c0f5d100>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2007040, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1749810538809862586, "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:": "gAWViAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWFAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLFIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_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": 392, "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, "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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 20, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.0-37-amd64-x86_64-with-glibc2.36 # 1 SMP PREEMPT_DYNAMIC Debian 6.1.140-1 (2025-05-22)", "Python": "3.11.2", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.7.1+cu126", "GPU Enabled": "True", "Numpy": "2.3.0", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}

ppo_lunarlander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32640db7641cb70ba87f941c5b97aff05bca8073899f474fe628ba271624e08
+oid sha256:78766a370ca9dd3fbbe05f06951186efc1de9237766b64bb7073d02ebce507f4
 size 149893

ppo_lunarlander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7f638e4e8e00>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f638e4e8ea0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f638e4e8f40>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f638e4e8fe0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f638e4e9080>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f638e4e9120>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f638e4e91c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f638e4e9260>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f638e4e9300>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f638e4e93a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f638e4e9440>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f638e4e94e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f77c0ee8e00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f77c0ee8ea0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f77c0ee8f40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77c0ee8fe0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f77c0ee9080>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f77c0ee9120>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f77c0ee91c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f77c0ee9260>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f77c0ee9300>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77c0ee93a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f77c0ee9440>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77c0ee94e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f638e4d7f00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f77c0f5d100>"
     },
     "verbose": 1,
     "policy_kwargs": {},

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fb0f1b00e558dae81d2641beb79ef14e34cbbac64c4828f80c206d05a94221d
-size 152518
+oid sha256:ad7753f479dd1ee1f73913cfad3cfd50e5fcdc0ca3b016a9e388083d75d85007
+size 145738

results.json

@@ -1 +1 @@
-{"mean_reward": 250.98770340620163, "std_reward": 65.46413970021803, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-13T13:28:42.996109"}
+{"mean_reward": 275.3190764914988, "std_reward": 15.612948431540113, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-17T18:30:47.193559"}