lunar lander v3 agent upload

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 270.18 +/- 19.68
+      value: 248.49 +/- 19.29
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 416, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7dcfb8530d60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dcfb8530e00>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dcfb8530ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dcfb8530f40>", "_build": "<function ActorCriticPolicy._build at 0x7dcfb8530fe0>", "forward": "<function ActorCriticPolicy.forward at 0x7dcfb8531080>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7dcfb8531120>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dcfb85311c0>", "_predict": "<function ActorCriticPolicy._predict at 0x7dcfb8531260>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dcfb8531300>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dcfb85313a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7dcfb8531440>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dcfb87d0c40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 31424, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1791254816596412284, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.983616, "_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": 252, "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": null, "high_repr": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.998, "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", "__firstlineno__": 343, "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7dcfb86a8f40>", "reset": "<function RolloutBuffer.reset at 0x7dcfb86a8fe0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7dcfb86a9080>", "add": "<function RolloutBuffer.add at 0x7dcfb86a9120>", "get": "<function RolloutBuffer.get at 0x7dcfb86a91c0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7dcfb86a9260>", "__static_attributes__": ["actions", "advantages", "episode_starts", "full", "gae_lambda", "gamma", "generator_ready", "log_probs", "observations", "returns", "rewards", "values"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dcfb8699140>"}, "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-6.6.122+-x86_64-with-glibc2.39 # 1 SMP Thu Apr 30 18:17:14 UTC 2026", "Python": "3.13.15", "Stable-Baselines3": "2.9.0", "PyTorch": "2.11.0+cu130", "GPU Enabled": "True", "Numpy": "2.1.3", "Cloudpickle": "3.1.2", "Gymnasium": "1.3.0", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 416, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7e2463289ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e2463289f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e246328a020>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e246328a0c0>", "_build": "<function ActorCriticPolicy._build at 0x7e246328a160>", "forward": "<function ActorCriticPolicy.forward at 0x7e246328a200>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e246328a2a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e246328a340>", "_predict": "<function ActorCriticPolicy._predict at 0x7e246328a3e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e246328a480>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e246328a520>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e246328a5c0>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e2463a58b80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1791268694198584591, "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:": "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:": "gAWVOQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGHvkhRqGlCMAWyUTegDjAF0lEdAlLTwQ6IWQHV9lChoBkdAZfbDw6QvH2gHTegDaAhHQJTbvvQWvbJ1fZQoaAZHQGMW7eMyaeBoB03oA2gIR0CU3f0G/vfCdX2UKGgGR0BcFBT850bMaAdN6ANoCEdAlN+WI42jwnV9lChoBkdAYVxR1oxpL2gHTegDaAhHQJTi4eIVM251fZQoaAZHQGyDr1uivgZoB03WAWgIR0CU40j2zv7WdX2UKGgGR0BwfWTEBKcvaAdNvAJoCEdAlOULI5o4/HV9lChoBkdAYb9a9sabWmgHTegDaAhHQJTthtALRa51fZQoaAZHQF6umZE2HcloB03oA2gIR0CU7aEMb3oLdX2UKGgGR0BejRjjJdSmaAdN6ANoCEdAlO7MSCe2/nV9lChoBkdAY4mSOBDohmgHTegDaAhHQJTwUjPfKp11fZQoaAZHQGc5ryUcGTtoB03oA2gIR0CU8q8gZCOWdX2UKGgGR0BgqhgogFHKaAdN6ANoCEdAlPwiZF5OanV9lChoBkdAYsoD9wWFe2gHTegDaAhHQJT/J0GNaQp1fZQoaAZHQGTXMpPRArxoB03oA2gIR0CVCatvXK8tdX2UKGgGR0BlpEajvd/KaAdN6ANoCEdAlQ5R4MWoFXV9lChoBkdAYVpGo73fymgHTegDaAhHQJURUPI4lyB1fZQoaAZHQFEZ3wkPcztoB01TAWgIR0CVGGoqTbFkdX2UKGgGR0BkJi704BFNaAdN6ANoCEdAlTdLpJPIn3V9lChoBkdAY78FlkH2RWgHTegDaAhHQJU6QdXDFZR1fZQoaAZHQHBhDx0+1ShoB038AmgIR0CVOt0UGmk4dX2UKGgGR0BmM/kT6BRRaAdN6ANoCEdAlTulKXfIjnV9lChoBkdAZK38E3bVSWgHTegDaAhHQJU+KxfOUt91fZQoaAZHQGUeFyJbdJtoB03oA2gIR0CVPotsN2C/dX2UKGgGR0BkqQKpkwvhaAdN6ANoCEdAlT/mOAAhjnV9lChoBkdAY0L9fCyhSWgHTegDaAhHQJVGp9uxbB51fZQoaAZHQGXxIIF/x2BoB03oA2gIR0CVR7rsByS3dX2UKGgGR0BmRzKaG5+ZaAdN6ANoCEdAlUk2uHN5dHV9lChoBkdAbpuJ4SpR42gHTT4DaAhHQJVKRh+fAbh1fZQoaAZHQGdLVLrX18NoB03oA2gIR0CVS5Q40dildX2UKGgGR0Bwj6JDVpbmaAdNzgJoCEdAlUzjUAksz3V9lChoBkfAA3qwhW5pamgHTTABaAhHQJVOILPUrkN1fZQoaAZHQG79laB7NStoB02YA2gIR0CVXjUzbeuWdX2UKGgGR0BxHZk9U0emaAdNmAJoCEdAlV5pFspG4XV9lChoBkdAZihOeJ53T2gHTegDaAhHQJVqZQ40dil1fZQoaAZHQGSGbAtWdVhoB03oA2gIR0CVdAvKlpGndX2UKGgGR0BtYWU2UB4maAdNmAJoCEdAlXon+6y0KXV9lChoBkdAY4CHSF49o2gHTegDaAhHQJWUYegctGx1fZQoaAZHQGIuXW4EwFloB03oA2gIR0CVlSFSsKb8dX2UKGgGR0BfLnI6r/83aAdN6ANoCEdAlZYteD3/P3V9lChoBkdAYyWwKSgXdmgHTegDaAhHQJWa89q1w5x1fZQoaAZHQGGn+armyPdoB03oA2gIR0CVnifnOjZddX2UKGgGR0BBse717IDHaAdL2mgIR0CVph1KXfIkdX2UKGgGR0Bjw74+KTB7aAdN6ANoCEdAlagU+1SflXV9lChoBkdAcZ8KifxtpGgHTYkDaAhHQJWqwX1rZap1fZQoaAZHQF7t4yoGY8doB03oA2gIR0CVqw69CeEqdX2UKGgGR0Bi8+xD9fkWaAdN6ANoCEdAlaw/vKEFn3V9lChoBkdAZGIiILw4KmgHTegDaAhHQJWthAbADaJ1fZQoaAZHQEtJWcz67/ZoB00OAWgIR0CVrd6lLvkSdX2UKGgGR0BizH6uW8h+aAdN6ANoCEdAla6+GfwqiHV9lChoBkdANCz5GjKxLWgHS/doCEdAlbuiYG+sYHV9lChoBkdANDTpHI6sAGgHS+loCEdAlbvkyHmA9XV9lChoBkdAZDV0mMOwxGgHTegDaAhHQJW+M2S+xnp1fZQoaAZHQGSjP6CUX55oB03oA2gIR0CVvmGc4HX3dX2UKGgGR0Bx3dxR2r4naAdNlANoCEdAlcC5Wq94/3V9lChoBkdAZ66abWmP52gHTegDaAhHQJXOFE2HclB1fZQoaAZHQGJ3n/T9bX9oB03oA2gIR0CV1SmIj4YadX2UKGgGR0Bh/sH4XXRPaAdN6ANoCEdAle8RhQWN3nV9lChoBkdAbB5+1jRUm2gHTagBaAhHQJXvXc580DV1fZQoaAZHQGEmYmCyyD9oB03oA2gIR0CV79J0GNaRdX2UKGgGR0Bx/rgIhQnAaAdNgAFoCEdAlfFF/tpmE3V9lChoBkdAY+yxwhnrZGgHTegDaAhHQJX0BBhQWN51fZQoaAZHQE2YfIS13MZoB0vraAhHQJX2ttpEhJR1fZQoaAZHQGWxO3trsSloB03oA2gIR0CV+UxcmjTKdX2UKGgGR0BvoLgjyFwlaAdNTwJoCEdAlfl0MTewcHV9lChoBkdAO/39m6GxlmgHS9VoCEdAlfnHPu5SWXV9lChoBkdAX3FozvZyuWgHTegDaAhHQJX6s5bQkX11fZQoaAZHQDIVZLZi/fxoB0vqaAhHQJX7MHD76551fZQoaAZHQGP8JNbkfcNoB03oA2gIR0CV/If4yoGZdX2UKGgGR0BhbgMx46fbaAdN6ANoCEdAlfy99x6v7nV9lChoBkdAZC0hBZ6lcmgHTegDaAhHQJX9gcsDnvF1fZQoaAZHQGIPqEnLJS1oB03oA2gIR0CV/ob7TDwZdX2UKGgGR0BuRONo8IRiaAdNLQJoCEdAlgMTfixVyXV9lChoBkdAcFv5gPVd5mgHTYABaAhHQJYMVtoBaLZ1fZQoaAZHQGUGqUu+RHRoB03oA2gIR0CWDvNb1RLsdX2UKGgGR0BjeJkEs8PnaAdN6ANoCEdAlhFo8ZDRdHV9lChoBkdAcqglpXZGrmgHTUABaAhHQJYhLjFQ2uR1fZQoaAZHQGcK1clgMMJoB03oA2gIR0CWQgJ79hqkdX2UKGgGR0Bm5pigCfYjaAdN6ANoCEdAlkT2SZBsynV9lChoBkdAbzgSrYGt62gHTbEBaAhHQJZFs/iYLLJ1fZQoaAZHQEN0IeHSF49oB0vYaAhHQJZG3EfkmyB1fZQoaAZHQFxvied07r9oB03oA2gIR0CWSD0KJEYwdX2UKGgGR0BuPS6jFhoeaAdNOwNoCEdAlknuizsyBXV9lChoBkdAZkp9Aood/GgHTegDaAhHQJZN/Ta0x/N1fZQoaAZHQF82h86V+qloB03oA2gIR0CWTiTs6aLGdX2UKGgGR0Bej8gMc6vJaAdN6ANoCEdAlk6H4CZF5XV9lChoBkdAR1lcOby6MGgHS+toCEdAlk9SV4X403V9lChoBkdAZujA0Kqn32gHTegDaAhHQJZPbNke6qd1fZQoaAZHQF9sjj7yhBZoB03oA2gIR0CWT9/6O5rhdX2UKGgGR0A/N56t1ZDBaAdL4mgIR0CWUMMQmNR4dX2UKGgGR0BkU/AfuCwsaAdN6ANoCEdAllEgeJYT03V9lChoBkdAZANEDyOJcmgHTegDaAhHQJZRT6zmfXh1fZQoaAZHQGIs5Gax5cFoB03oA2gIR0CWUuc6NlyzdX2UKGgGR0Bkg3rjYI0JaAdN6ANoCEdAllYFwT/Q0HV9lChoBkdAQ+hd2Pkq+mgHS+doCEdAllkXW4EwFnV9lChoBkdAcejJaJQ+EGgHTRkBaAhHQJZasptrKvF1fZQoaAZHQGNMrksBhhJoB03oA2gIR0CWX8W1twaSdX2UKGgGR0BDoL+YMOPOaAdLwWgIR0CWZMXp4bCKdX2UKGgGR0BwwxuqFRHgaAdNZAFoCEdAlmaD6vaDf3V9lChoBkdAcWlFo+Ofd2gHTVoDaAhHQJZ5LmW+oLp1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 248, "n_steps": 1024, "gamma": 0.998, "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", "__firstlineno__": 343, "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7e24633ea020>", "reset": "<function RolloutBuffer.reset at 0x7e24633ea0c0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7e24633ea160>", "add": "<function RolloutBuffer.add at 0x7e24633ea200>", "get": "<function RolloutBuffer.get at 0x7e24633ea2a0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7e24633ea340>", "__static_attributes__": ["actions", "advantages", "episode_starts", "full", "gae_lambda", "gamma", "generator_ready", "log_probs", "observations", "returns", "rewards", "values"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e24633a1980>"}, "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, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVxQEAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCIWUjANsb3eUjBNudW1weS5fY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoliAAAAAAAAAAAAAgwAAAIMAAACDBAAAgwdsPycAAACDBAAAAgAAAAICUaAtLCIWUjAFDlHSUUpSMDWJvdW5kZWRfYmVsb3eUaBMolggAAAAAAAAAAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUaBZ0lFKUjARoaWdolGgTKJYgAAAAAAAAAAAAIEAAACBAAAAgQQAAIEHbD8lAAAAgQQAAgD8AAIA/lGgLSwiFlGgWdJRSlIwNYm91bmRlZF9hYm92ZZRoEyiWCAAAAAAAAAABAQEBAQEBAZRoHUsIhZRoFnSUUpSMCGxvd19yZXBylE6MCWhpZ2hfcmVwcpROjApfbnBfcmFuZG9tlE51Yi4=", "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": null, "high_repr": null, "_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, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-6.6.122+-x86_64-with-glibc2.39 # 1 SMP Thu Apr 30 18:17:14 UTC 2026", "Python": "3.13.15", "Stable-Baselines3": "2.9.0", "PyTorch": "2.11.0+cu130", "GPU Enabled": "True", "Numpy": "2.1.3", "Cloudpickle": "3.1.2", "Gymnasium": "1.3.0", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9d0b74ce0deb769ee575d884563de666651da0ee2a43226f69b52364f25b4c5
-size 149672
+oid sha256:cdd9ad2a35bd8f5a45b90ec411a110ffa0c1ab657f66fe0d734185f949047050
+size 150587

ppo-LunarLander-v3/data

@@ -5,18 +5,18 @@
         "__module__": "stable_baselines3.common.policies",
         "__firstlineno__": 416,
         "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x7dcfb8530d60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dcfb8530e00>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dcfb8530ea0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dcfb8530f40>",
-        "_build": "<function ActorCriticPolicy._build at 0x7dcfb8530fe0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7dcfb8531080>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7dcfb8531120>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dcfb85311c0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7dcfb8531260>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dcfb8531300>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dcfb85313a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7dcfb8531440>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7e2463289ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e2463289f80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e246328a020>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e246328a0c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7e246328a160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7e246328a200>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e246328a2a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e246328a340>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7e246328a3e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e246328a480>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e246328a520>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e246328a5c0>",
         "__static_attributes__": [
             "action_dist",
             "action_net",
@@ -37,21 +37,21 @@
             "vf_features_extractor"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7dcfb87d0c40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7e2463a58b80>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 31424,
+    "num_timesteps": 1015808,
     "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1791254816596412284,
+    "start_time": 1791268694198584591,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -61,42 +61,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.983616,
+    "_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": 252,
-    "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": null,
-        "high_repr": null,
-        "_np_random": null
-    },
-    "action_space": {
-        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu",
-        "dtype": "int64",
-        "n": "4",
-        "start": "0",
-        "_shape": [],
-        "_np_random": null
-    },
-    "n_envs": 16,
+    "_n_updates": 248,
     "n_steps": 1024,
     "gamma": 0.998,
     "gae_lambda": 0.98,
@@ -110,12 +85,12 @@
         "__firstlineno__": 343,
         "__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__": "\nRollout buffer used in on-policy algorithms like A2C/PPO.\nIt corresponds to ``buffer_size`` transitions collected\nusing the current policy.\nThis experience will be discarded after the policy update.\nIn order to use PPO objective, we also store the current value of each state\nand the log probability of each taken action.\n\nThe term rollout here refers to the model-free notion and should not\nbe used with the concept of rollout used in model-based RL or planning.\nHence, 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 0x7dcfb86a8f40>",
-        "reset": "<function RolloutBuffer.reset at 0x7dcfb86a8fe0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7dcfb86a9080>",
-        "add": "<function RolloutBuffer.add at 0x7dcfb86a9120>",
-        "get": "<function RolloutBuffer.get at 0x7dcfb86a91c0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7dcfb86a9260>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7e24633ea020>",
+        "reset": "<function RolloutBuffer.reset at 0x7e24633ea0c0>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7e24633ea160>",
+        "add": "<function RolloutBuffer.add at 0x7e24633ea200>",
+        "get": "<function RolloutBuffer.get at 0x7e24633ea2a0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7e24633ea340>",
         "__static_attributes__": [
             "actions",
             "advantages",
@@ -131,7 +106,7 @@
             "values"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7dcfb8699140>"
+        "_abc_impl": "<_abc._abc_data object at 0x7e24633a1980>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,
@@ -144,6 +119,31 @@
     "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",
+        "_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": null,
+        "high_repr": null,
+        "_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,
     "lr_schedule": {
         ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
         ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu",

ppo-LunarLander-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc0a0e11b251955865ecbd7c38273d736f2409eb4ec3e06d883b35a0e7c0258
-size 88695
+oid sha256:82da61847a2eec0a6fd0750ee5f8607dee0b3506a9ec89b74b14ae19eb7f97f4
+size 88887

ppo-LunarLander-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd452de219007c69ae0b18681a7389c0cb042794be7ba6e7e781fd6391482be
+oid sha256:d8f19963ec6ef37e9d47b3a304259d7b58d01f822ba1a828007d291424f67497
 size 44095

results.json

@@ -1 +1 @@
-{"mean_reward": 270.1845648, "std_reward": 19.67920570389709, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-06T02:58:08.567518"}
+{"mean_reward": 248.49214910000006, "std_reward": 19.29340319070313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-10-06T07:10:33.596648"}