completed basic lunar lander agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -167.83 +/- 59.63
+      value: 271.14 +/- 12.51
       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 0x7c8dcc4b85e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c8dcc4b8680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c8dcc4b8720>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c8dcc4b87c0>", "_build": "<function ActorCriticPolicy._build at 0x7c8dcc4b8860>", "forward": "<function ActorCriticPolicy.forward at 0x7c8dcc4b8900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c8dcc4b89a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c8dcc4b8a40>", "_predict": "<function ActorCriticPolicy._predict at 0x7c8dcc4b8ae0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c8dcc4b8b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c8dcc4b8c20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c8dcc4b8cc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c8dcc4458c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "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 0x7c8dcc4b85e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c8dcc4b8680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c8dcc4b8720>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c8dcc4b87c0>", "_build": "<function ActorCriticPolicy._build at 0x7c8dcc4b8860>", "forward": "<function ActorCriticPolicy.forward at 0x7c8dcc4b8900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c8dcc4b89a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c8dcc4b8a40>", "_predict": "<function ActorCriticPolicy._predict at 0x7c8dcc4b8ae0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c8dcc4b8b80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c8dcc4b8c20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c8dcc4b8cc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c8dcc4458c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1769483657358803768, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdgIAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAIAAAAAAADNhy69ruOEPz0Cxr2i8Aq/6sR/vbpV67wAAAAAAAAAAEZHCr4d2r4/MjQIv81gD75GRhW+XmSkvgAAAAAAAAAA0zsEPpjolj49dPk75IFgvigjMj3eLrA9AAAAAAAAAADa0Eo+QUyivCDDojsRYAi6W9UPvnIV17oAAIA/AACAP20kJ75Spa8/YC0Gv3N55L5Nnye++BEsvgAAAAAAAAAAgEPYPVJ4/rlOiYQznqvxLlS2GLuOHq6zAAAAAAAAgD+tLgC+uGiJu7EXLL2YZoI8hNGKPNSkjj0AAIA/AACAP6CiLT4fBrW7cmOQvJxq8jxJWAC9rgzJPQAAgD8AAIA/U4Fmvko+Oj4+nlk+3Qi4viI6Lj620Uc+AAAAAAAAAAAzExm9EIHFPlUPv72730S+v2KdvQqgJj0AAAAAAAAAAA0AmD57v1k/46eGvXvt0b78XN092lOxvQAAAAAAAAAAWmSWPuFN/D6VUeu9/zGyvsDExT1tTEW9AAAAAAAAAACAYZi+Qh9MP7q3dz1X9sq+fkAnvlrjxj0AAAAAAAAAAE1DH70pyG+6eB3yOYkRPbbcPUK6EZwNuQAAgD8AAIA/miNzvFxDXLogCBa6onsSteKg4LhqYzA5AACAPwAAgD8z8Mw8pCg3u1ODabw502k8JnlfPErcSb0AAIA/AACAP5SMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsIhpSMAUOUdJRSlC4="}, "_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": -0.015808000000000044, "_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": 310, "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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct  2 10:42:05 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68ccb4d23d02bda2b38a32d83b3ffca5396edea0cce047540e2958ddfd66550
-size 55209
+oid sha256:6b039a4e7fef2bbd9968b3285e088696ce91abd78cb2b7fc33908bb660fe63d0
+size 148071

ppo-LunarLander-v2/data

@@ -21,25 +21,37 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1769483657358803768,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": 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": 1.0,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHDsu4Cp3ouMAWyUTQIBjAF0lEdAorGuVC5VfnV9lChoBkdAbkrrVvuPWGgHTQABaAhHQKKyLesPrfN1fZQoaAZHQGxSREORT0hoB00CAWgIR0CissDKPn0TdX2UKGgGR0BvU/jS5RTCaAdL9GgIR0CisxZ7w8W9dX2UKGgGR0BycNLBbfP5aAdNVwFoCEdAorOcAeaKDXV9lChoBkdAb0OplSS/02gHTQYBaAhHQKK0HNIsiB51fZQoaAZHQHI8yqlxffJoB01RAWgIR0CitH+so2GZdX2UKGgGR0BytbUvwmVraAdL6mgIR0CitN7iqABldX2UKGgGR0BsHo7xNIsiaAdL8GgIR0CitN+G47RwdX2UKGgGR0Bj7F+7UXpGaAdN6ANoCEdAorVL56+nInV9lChoBkdAb7qKEWZZ0WgHTQEBaAhHQKK1X/YJ3Pl1fZQoaAZHQHMdT0cwQDpoB0v9aAhHQKK1X/XGwRp1fZQoaAZHQG43cwHqu8toB0v/aAhHQKK2CVfNRm91fZQoaAZHQHDD6xxDLKVoB00uAWgIR0Cito4C6pYLdX2UKGgGR0Btx8J6Y3NtaAdL7GgIR0CituwdKdxydX2UKGgGR0Bw1XIfbKzSaAdNFwFoCEdAordkvsZ5zHV9lChoBkdAcbHfFrEcbWgHTS0BaAhHQKK39B7eEZl1fZQoaAZHQHDvnRCx/utoB00AAWgIR0CiuBlkQPI5dX2UKGgGR0BhEJrJr+HaaAdN6ANoCEdAorgeSKWLP3V9lChoBkdAcDbC/oJRfmgHTQABaAhHQKK4Yh8IAwR1fZQoaAZHQHDLshouf29oB00BAWgIR0CiuNnkkrwwdX2UKGgGR0BupMEeQuEmaAdNCgFoCEdAormD9ZRsM3V9lChoBkdAcEB5yEL6UWgHTQABaAhHQKK6VL/S6Ud1fZQoaAZHQG5AqaG5+YtoB00WAWgIR0CiunN0V8CxdX2UKGgGR0Bt+q3Td+G5aAdNBQFoCEdAorp7nq3VkXV9lChoBkdAb3qSB9TgmGgHTRkBaAhHQKK7pCTEBKd1fZQoaAZHQG+EMsxwhntoB00FAWgIR0CivD4MF2V3dX2UKGgGR0BvAEENe+mFaAdL72gIR0CivFP114gSdX2UKGgGR0AxBaqS5iEyaAdL12gIR0CivLML4N7TdX2UKGgGR0BxCIxxkupTaAdNCAFoCEdAor29cOby6XV9lChoBkdAb8v9kz41xmgHS/NoCEdAor5zHQyAQXV9lChoBkdAcCunxri2lWgHS/BoCEdAor6VZRsMzHV9lChoBkdAb+IiUxEfDGgHS/hoCEdAor8h5TqB3HV9lChoBkdAbgs6xxDLKWgHTQkBaAhHQKK/LTcZccF1fZQoaAZHQG5INY8uBc1oB02wAWgIR0Civ/UkGA09dX2UKGgGR0Bvq1mBe5WjaAdNAAFoCEdAosCQmsvIwXV9lChoBkdAb2gwt8NQTGgHTQMBaAhHQKLBQHSnccl1fZQoaAZHQG991rRBu4xoB00TAWgIR0CiwblTm4iHdX2UKGgGR0BxlRJDmbLEaAdNEQFoCEdAosKwQnQY13V9lChoBkdAcKeDdgv12GgHS+ZoCEdAosNNfiPyTnV9lChoBkdAcbZNNahYeWgHTQgBaAhHQKLDWkrPMSt1fZQoaAZHQHIlqTW5H3FoB00bAWgIR0Ciw3K94/u9dX2UKGgGR0BxYU4ZMtbtaAdNKAFoCEdAosPMZDRc/3V9lChoBkdAcVdINEw352gHS+loCEdAosPSaZx7zHV9lChoBkdAcAKavzOHFmgHTRUBaAhHQKLE16JIlMR1fZQoaAZHQHEZFNtZV4poB00BAWgIR0CixP30oSctdX2UKGgGR0Bxz0NEw35vaAdNGAFoCEdAosZKyMUAUHV9lChoBkdAb+hvoePq92gHTeQBaAhHQKLGcxlg+hZ1fZQoaAZHQG7NDst03fhoB00SAWgIR0Cix3cE3bVSdX2UKGgGR0Bw0WX7cfvGaAdNNAFoCEdAoseXX05EMXV9lChoBkdAccc1W8yvcWgHS+xoCEdAosf/7k4m1XV9lChoBkdAcRlIyCWeH2gHS/hoCEdAosjvnuAqeHV9lChoBkdAcGzAz544ZWgHTQ0BaAhHQKLJbHZK3/h1fZQoaAZHQHGfhmTTvy9oB0v4aAhHQKLJcs4DLbJ1fZQoaAZHQG9zQ/xDst1oB00MAWgIR0CiyeZ08vEkdX2UKGgGR0BxIwMrmQr+aAdNCAFoCEdAosrfrY5DJHV9lChoBkdAcTjPC2tuDWgHTaMBaAhHQKLLVZGrjo91fZQoaAZHQHBwqVY6nzhoB00oAWgIR0Ciy8wZwXImdX2UKGgGR0BwWE8yN4qxaAdL/2gIR0CizDnmRvFWdX2UKGgGR0BwvdNYbKigaAdNAwFoCEdAosx6Ww/xD3V9lChoBkdAcXyof0VafWgHTZYBaAhHQKLMqi8nNPh1fZQoaAZHQF3MwJgLJCBoB03oA2gIR0CizPDG1hLHdX2UKGgGR0BtQHSF49owaAdL72gIR0CizRXirDIjdX2UKGgGR0BvC6Cz1K5DaAdL+GgIR0CizaG4I8hcdX2UKGgGR0BsODojfNzKaAdL62gIR0Cizp7Vz6rOdX2UKGgGR0BsECDXe3x4aAdL+2gIR0CizvIDxLCfdX2UKGgGR0BxmwLBsQ/YaAdNHgFoCEdAos9TTUiIL3V9lChoBkdAcVPrTH80lGgHS/FoCEdAotA4fOlfq3V9lChoBkdAYSHv4M4LkWgHTegDaAhHQKLQtfvWpZR1fZQoaAZHQG+0O8scyWRoB004AWgIR0Ci0NccU/OddX2UKGgGR0Bxd1XQtz0ZaAdL/2gIR0Ci0PFmOEM9dX2UKGgGR0Bt41gSeyzHaAdL7GgIR0Ci0Pd4/u9fdX2UKGgGR0ByiSaa1Cw9aAdL/WgIR0Ci0awyIpH7dX2UKGgGR0BwYuplz2eyaAdL5GgIR0Ci0dPmgam5dX2UKGgGR0BtjujGkvboaAdL+2gIR0Ci0mzXjENwdX2UKGgGR0BtoIDcM3IdaAdNDwFoCEdAotJtfb9IgHV9lChoBkdAcXQAi3XqaGgHTSQBaAhHQKLSrmU4aP11fZQoaAZHQHD8pQxesxRoB00cAWgIR0Ci1Bjd56dEdX2UKGgGR0Bsq2scQyylaAdNHAFoCEdAotV5BiTdL3V9lChoBkdAcHcqZ+hGpmgHTRABaAhHQKLVl66asp51fZQoaAZHQHKsJiAlOXVoB00GAWgIR0Ci1cp++dsjdX2UKGgGR0BfScP4EfT1aAdN6ANoCEdAotZtgSeyzHV9lChoBkdAcXPgG8mKImgHS/RoCEdAotaAJPZZjnV9lChoBkdAcJHdELH+62gHS+toCEdAotcxa9sabXV9lChoBkdAbsw/cnE2pGgHTREBaAhHQKLYDd7fHgh1fZQoaAZHQG9tyU9pyp9oB00QAWgIR0Ci2Cc89wFUdX2UKGgGR0BxSSJgssg/aAdNEwFoCEdAothUu14PgHV9lChoBkdAcQY4RmK64GgHS+JoCEdAotjOn0kGA3V9lChoBkdAcPlGetjkMmgHTRIBaAhHQKLZKDIRywR1fZQoaAZHQHE2gRK6FuhoB00bAWgIR0Ci2Sz850bMdX2UKGgGR0Bw+rVpblijaAdL72gIR0Ci2UechC+ldX2UKGgGR0BwNRnPE87qaAdL62gIR0Ci2xEdeY2LdX2UKGgGR0Bw6vxwyZa3aAdNHQFoCEdAotsXRsuWbHV9lChoBkdAcmdhGH58B2gHTW0BaAhHQKLbfnBciW51fZQoaAZHQG1KwIMSbphoB00PAWgIR0Ci27/dqL0jdX2UKGgGR0BxLAy57PY4aAdNCgFoCEdAotvUQI2OyXV9lChoBkdAcbvBNEgGKWgHS99oCEdAotvesYEW7HV9lChoBkdAcRlNBF/hEWgHTRQBaAhHQKLcbGd7OVx1fZQoaAZHQHCO+6iCaqloB0v8aAhHQKLc+Bp5/sp1fZQoaAZHQHBP/YODrZ9oB0v1aAhHQKLdHSWqtHR1ZS4="
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 310,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
-size 1120
+oid sha256:4fb5f212c60147d3edff7a720ac8b125971b7d2342bc732815187506f414c26b
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fa1625d62def523b250aa176ccb87e718aecdc7fddfa548f2610d871cacc2d9
+oid sha256:af7f00a3366d64681ec5bd8dc0c173e09632942079e2f56c2d86df722ca00268
 size 43762

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7bbb2fc8b86f229ddc6f777df7a50965aefa26798f6e29ba365be1d5d9db6e
-size 182573
+oid sha256:721514f2a73ac83fccc668096fa7c471a30209190a1268154ae3fc7079a87b1e
+size 157602

results.json

@@ -1 +1 @@
-{"mean_reward": -167.8252738, "std_reward": 59.63339793644567, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-27T03:11:58.217032"}
+{"mean_reward": 271.143363, "std_reward": 12.505171757103723, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-27T04:05:03.313143"}