5th lunar lander to push

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 273.06 +/- 21.45
+      value: 277.38 +/- 31.23
       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 0x780045866560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7800458665f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x780045866680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x780045866710>", "_build": "<function ActorCriticPolicy._build at 0x7800458667a0>", "forward": "<function ActorCriticPolicy.forward at 0x780045866830>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7800458668c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x780045866950>", "_predict": "<function ActorCriticPolicy._predict at 0x7800458669e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x780045866a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x780045866b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x780045866b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78004586c040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705952740553290342, "learning_rate": 0.0005941759020864799, "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": 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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.9989918334349422, "gae_lambda": 0.9560281871170067, "ent_coef": 0.0023928414761823316, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 5, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "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 0x780045866560>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7800458665f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x780045866680>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x780045866710>", "_build": "<function ActorCriticPolicy._build at 0x7800458667a0>", "forward": "<function ActorCriticPolicy.forward at 0x780045866830>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7800458668c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x780045866950>", "_predict": "<function ActorCriticPolicy._predict at 0x7800458669e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x780045866a70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x780045866b00>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x780045866b90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78004586c040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705954952176743896, "learning_rate": 0.0005941759020864799, "tensorboard_log": null, "_last_obs": null, "_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:": "gAWV7wsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHGr3hwVCX2MAWyUTQEBjAF0lEdAlJA9BfKISHV9lChoBkdAcZqzzErGzmgHS8xoCEdAlJBz6SDAanV9lChoBkdAc4tGdI5HVmgHTQABaAhHQJSQ3hBJI2B1fZQoaAZHQHNFRLf1pTNoB0vnaAhHQJSRQob4rSV1fZQoaAZHQHEGwjps41hoB0vfaAhHQJSSaDmKZUl1fZQoaAZHQGLrmvfTCtRoB03oA2gIR0CUkprWRRuTdX2UKGgGR0Bx2NZDArQPaAdL5WgIR0CUlBUXpGF0dX2UKGgGR0BxrNU83dbgaAdL4GgIR0CUlExwyZa3dX2UKGgGR0BzLEdbPhQ4aAdL4mgIR0CUlKipNsWPdX2UKGgGR0BwEOBSUC7saAdL+2gIR0CUlO5Pdl/ZdX2UKGgGR0Bw3VD7ZWaMaAdL2mgIR0CUlfn8sMAndX2UKGgGR0By1EkgOjIraAdNHAFoCEdAlJaBWT5ft3V9lChoBkdAclfDoyKvV2gHS9toCEdAlJcltwaR6nV9lChoBkdAcYMad+Xqq2gHS9toCEdAlJeB+vyLAHV9lChoBkdAcp9VQQ+UyGgHTQkBaAhHQJSX55qubI91fZQoaAZHQHGBYN3GGVRoB0vbaAhHQJSX+BreqJd1fZQoaAZHQHAWtRzijtZoB0vqaAhHQJSYiElE7XB1fZQoaAZHQHLApxWDHwRoB00AAWgIR0CUmL+De0ojdX2UKGgGR0BzpYGTs6aLaAdL7WgIR0CUmNrgwXZXdX2UKGgGR0Bu2hrYXfqHaAdNAQFoCEdAlJmVjI7vHHV9lChoBkdAcUm9gWrOq2gHS+RoCEdAlJnQYDTz/nV9lChoBkdAb/HIikfs/2gHS+5oCEdAlJns0pEx7HV9lChoBkdAcVjO/tY0VWgHS8toCEdAlJpLPt2LYXV9lChoBkdAcCbZ00WM0mgHS9xoCEdAlJriyUs4DXV9lChoBkdAbYM0CRwIdGgHS/FoCEdAlJsPUWl/IHV9lChoBkdAcR3ZWq94/2gHS99oCEdAlJsnI6r/83V9lChoBkdAcKHvovBacWgHS+BoCEdAlJvbcsUZenV9lChoBkdAcd4GKAJ9iWgHS9loCEdAlJx5VKf4AXV9lChoBkdAceFBQvYe1mgHS+9oCEdAlJ1dwJgLJHV9lChoBkdAcen/m1YyPGgHTRIBaAhHQJSdiHsTnJV1fZQoaAZHQHEq/+CK77NoB0vPaAhHQJSdyZmZmZp1fZQoaAZHQHAyjrAxi5NoB0v1aAhHQJTMi89Oh011fZQoaAZHQHKmrZzxPO9oB0vyaAhHQJTM+fcvduZ1fZQoaAZHQHOCyLMs6JZoB00SAWgIR0CUzSza9K28dX2UKGgGR0ByiaN0eU6gaAdL2mgIR0CUzXq8DjiodX2UKGgGR0ByxLv+fh/BaAdLv2gIR0CUzY3lCCz1dX2UKGgGR0ByorAO8TSLaAdNBgFoCEdAlM3HQUpNK3V9lChoBkdAcCh2r4nF52gHS99oCEdAlM3rZOBUaXV9lChoBkdAb8HtAs052mgHS+5oCEdAlM4jY/Vy3nV9lChoBkdAccRuiN83M2gHS9ZoCEdAlM7md7OVxHV9lChoBkdAcYNm1pj+aWgHS9xoCEdAlM72OQyRCHV9lChoBkdAcPe8/2TPjWgHS+loCEdAlM8XWjGkvnV9lChoBkdAcTAjB2wFDGgHS/RoCEdAlNBFabF0gnV9lChoBkdAct4c7QswtmgHS8VoCEdAlNCwBLf1pXV9lChoBkdAciObKRuCPWgHS/9oCEdAlNFDSG8Em3V9lChoBkdAcQ0fjS5RTGgHS+BoCEdAlNFb127nPnV9lChoBkdAcWmcbiqABmgHS/VoCEdAlNKT6SDAanV9lChoBkdAcFtA5aNdaGgHS/5oCEdAlNKdW6shgXV9lChoBkdAcQg3uNPxhGgHS/FoCEdAlNLvzFuNxXV9lChoBkdAcZSjnFHavmgHS/BoCEdAlNMhlxwQ2HV9lChoBkdAc4teuFHrhWgHS99oCEdAlNMfW6K+BnV9lChoBkdAcoKPnjhky2gHS+toCEdAlNNPnSv1UXV9lChoBkdAbyVXpW3jMmgHS9VoCEdAlNN6nR9gGHV9lChoBkdAcy5mjTKDCmgHS+toCEdAlNO4i9qUNnV9lChoBkdAcralHSWqtGgHTQABaAhHQJTUAeGO+7F1fZQoaAZHQHLT7DqGDcxoB0veaAhHQJTUcg8r7O51fZQoaAZHQG7/LQokRjBoB0vfaAhHQJTUnWXkYGd1fZQoaAZHQHErUc0cfeVoB0vyaAhHQJTU3rxAjY91fZQoaAZHQHMstfkWAPNoB0vcaAhHQJTVtj2Bas91fZQoaAZHQHDE3CXQdCFoB0vTaAhHQJTV6mpEQXh1fZQoaAZHQHHwYjv/io9oB0v1aAhHQJTXNGoaUA11fZQoaAZHQHCFwJTl1bJoB0vOaAhHQJTXe1stTUB1fZQoaAZHQHA01R+BpYdoB0vbaAhHQJTXy2uxKQJ1fZQoaAZHQHAQ1c2R7qpoB0vUaAhHQJTX+gZjx1B1fZQoaAZHQHGUMOG0u15oB0vTaAhHQJTYIIOYplV1fZQoaAZHQHEP0NSZSeloB0vQaAhHQJTYQu3+dbx1fZQoaAZHQHEaDtb9qDdoB0vPaAhHQJTYatZFG5N1fZQoaAZHQHAjJgCwKShoB0vqaAhHQJTYtPacqe91fZQoaAZHQG6HG7rcCYFoB0vPaAhHQJTYtIFvAGl1fZQoaAZHQHN4hNdqtYBoB0vdaAhHQJTZXECNjsl1fZQoaAZHQHMMcd5prUNoB0vnaAhHQJTaRnuiN851fZQoaAZHQHQOV9fCyhVoB0v6aAhHQJTamfJ3gUF1fZQoaAZHQHETElme18doB0vsaAhHQJTasRGtp251fZQoaAZHQHF820iQkopoB0v7aAhHQJTcF4HHFP11fZQoaAZHQHGU/y08eS1oB00AAWgIR0CU3HH8CPp7dX2UKGgGR0BxhjOiWVu8aAdL42gIR0CU3ROWSlnAdX2UKGgGR0BzcZobn5i3aAdL7GgIR0CU3aVsUIszdX2UKGgGR0Bx3iI0qH45aAdLymgIR0CU3btozvZzdX2UKGgGR0Bxl7Sc9W6taAdL6GgIR0CU3hYqXnhbdX2UKGgGR0Bxly9ugpSaaAdL42gIR0CU3ifBeokzdX2UKGgGR0BydCO4oZydaAdL2GgIR0CU3oUn5SFXdX2UKGgGR0BuB9hCtzS1aAdNAAFoCEdAlN6f24/eL3V9lChoBkdAcv/SVnmJWWgHS/FoCEdAlN62uLaVU3V9lChoBkdAcUDQ5FPSD2gHS/9oCEdAlN95TyauwHV9lChoBkdAcws5vcafjGgHS9JoCEdAlN/z3yqdYnV9lChoBkdAbYRKe05U+GgHS9JoCEdAlOBWEPDpDHV9lChoBkdAcwf225QP7WgHTQwBaAhHQJTgfoPkJa91fZQoaAZHQG8K+kYXO4ZoB0vhaAhHQJTgn1SOzY51fZQoaAZHQHKRmuHN5dJoB0vvaAhHQJTiwlSjxkN1fZQoaAZHQHCFygCfYjBoB0vXaAhHQJTjQ/LTx5N1fZQoaAZHQHGZOHi3ocJoB0vdaAhHQJTjg9KVY6p1fZQoaAZHQHPZocNpdrxoB0vVaAhHQJTjnxsl9jR1fZQoaAZHQHE4229cry1oB0vtaAhHQJTkUMgEEDB1fZQoaAZHQG7mDSw4bS9oB0vlaAhHQJTkpjVhCt11fZQoaAZHQHM1qcmShaloB0voaAhHQJTkoysS00F1fZQoaAZHQHJobeyiVSpoB00JAWgIR0CU5XZnctXgdX2UKGgGR0BwhgjzI3iraAdL42gIR0CU5X+WnjyXdX2UKGgGR0Bx/mVopQUIaAdL12gIR0CU5bEzO5avdX2UKGgGR0ByW+1lXiiqaAdLymgIR0CU5eiTt9hJdX2UKGgGR0BynXFXJYDDaAdL1GgIR0CU5kr5ZbIMdWUu"}, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.9989918334349422, "gae_lambda": 0.9560281871170067, "ent_coef": 0.0023928414761823316, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 5, "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-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2-10.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c595163657c0b0e34dbfe374f2d699505b74379d66d11cd64ed374c7856244be
+size 147272

ppo-LunarLander-v2-10/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

ppo-LunarLander-v2-10/data

@@ -0,0 +1,96 @@
+{
+    "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 0x780045866560>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7800458665f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x780045866680>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x780045866710>",
+        "_build": "<function ActorCriticPolicy._build at 0x7800458667a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x780045866830>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7800458668c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x780045866950>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7800458669e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x780045866a70>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x780045866b00>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x780045866b90>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78004586c040>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1705954952176743896,
+    "learning_rate": 0.0005941759020864799,
+    "tensorboard_log": null,
+    "_last_obs": null,
+    "_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:": "gAWV7wsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHGr3hwVCX2MAWyUTQEBjAF0lEdAlJA9BfKISHV9lChoBkdAcZqzzErGzmgHS8xoCEdAlJBz6SDAanV9lChoBkdAc4tGdI5HVmgHTQABaAhHQJSQ3hBJI2B1fZQoaAZHQHNFRLf1pTNoB0vnaAhHQJSRQob4rSV1fZQoaAZHQHEGwjps41hoB0vfaAhHQJSSaDmKZUl1fZQoaAZHQGLrmvfTCtRoB03oA2gIR0CUkprWRRuTdX2UKGgGR0Bx2NZDArQPaAdL5WgIR0CUlBUXpGF0dX2UKGgGR0BxrNU83dbgaAdL4GgIR0CUlExwyZa3dX2UKGgGR0BzLEdbPhQ4aAdL4mgIR0CUlKipNsWPdX2UKGgGR0BwEOBSUC7saAdL+2gIR0CUlO5Pdl/ZdX2UKGgGR0Bw3VD7ZWaMaAdL2mgIR0CUlfn8sMAndX2UKGgGR0By1EkgOjIraAdNHAFoCEdAlJaBWT5ft3V9lChoBkdAclfDoyKvV2gHS9toCEdAlJcltwaR6nV9lChoBkdAcYMad+Xqq2gHS9toCEdAlJeB+vyLAHV9lChoBkdAcp9VQQ+UyGgHTQkBaAhHQJSX55qubI91fZQoaAZHQHGBYN3GGVRoB0vbaAhHQJSX+BreqJd1fZQoaAZHQHAWtRzijtZoB0vqaAhHQJSYiElE7XB1fZQoaAZHQHLApxWDHwRoB00AAWgIR0CUmL+De0ojdX2UKGgGR0BzpYGTs6aLaAdL7WgIR0CUmNrgwXZXdX2UKGgGR0Bu2hrYXfqHaAdNAQFoCEdAlJmVjI7vHHV9lChoBkdAcUm9gWrOq2gHS+RoCEdAlJnQYDTz/nV9lChoBkdAb/HIikfs/2gHS+5oCEdAlJns0pEx7HV9lChoBkdAcVjO/tY0VWgHS8toCEdAlJpLPt2LYXV9lChoBkdAcCbZ00WM0mgHS9xoCEdAlJriyUs4DXV9lChoBkdAbYM0CRwIdGgHS/FoCEdAlJsPUWl/IHV9lChoBkdAcR3ZWq94/2gHS99oCEdAlJsnI6r/83V9lChoBkdAcKHvovBacWgHS+BoCEdAlJvbcsUZenV9lChoBkdAcd4GKAJ9iWgHS9loCEdAlJx5VKf4AXV9lChoBkdAceFBQvYe1mgHS+9oCEdAlJ1dwJgLJHV9lChoBkdAcen/m1YyPGgHTRIBaAhHQJSdiHsTnJV1fZQoaAZHQHEq/+CK77NoB0vPaAhHQJSdyZmZmZp1fZQoaAZHQHAyjrAxi5NoB0v1aAhHQJTMi89Oh011fZQoaAZHQHKmrZzxPO9oB0vyaAhHQJTM+fcvduZ1fZQoaAZHQHOCyLMs6JZoB00SAWgIR0CUzSza9K28dX2UKGgGR0ByiaN0eU6gaAdL2mgIR0CUzXq8DjiodX2UKGgGR0ByxLv+fh/BaAdLv2gIR0CUzY3lCCz1dX2UKGgGR0ByorAO8TSLaAdNBgFoCEdAlM3HQUpNK3V9lChoBkdAcCh2r4nF52gHS99oCEdAlM3rZOBUaXV9lChoBkdAb8HtAs052mgHS+5oCEdAlM4jY/Vy3nV9lChoBkdAccRuiN83M2gHS9ZoCEdAlM7md7OVxHV9lChoBkdAcYNm1pj+aWgHS9xoCEdAlM72OQyRCHV9lChoBkdAcPe8/2TPjWgHS+loCEdAlM8XWjGkvnV9lChoBkdAcTAjB2wFDGgHS/RoCEdAlNBFabF0gnV9lChoBkdAct4c7QswtmgHS8VoCEdAlNCwBLf1pXV9lChoBkdAciObKRuCPWgHS/9oCEdAlNFDSG8Em3V9lChoBkdAcQ0fjS5RTGgHS+BoCEdAlNFb127nPnV9lChoBkdAcWmcbiqABmgHS/VoCEdAlNKT6SDAanV9lChoBkdAcFtA5aNdaGgHS/5oCEdAlNKdW6shgXV9lChoBkdAcQg3uNPxhGgHS/FoCEdAlNLvzFuNxXV9lChoBkdAcZSjnFHavmgHS/BoCEdAlNMhlxwQ2HV9lChoBkdAc4teuFHrhWgHS99oCEdAlNMfW6K+BnV9lChoBkdAcoKPnjhky2gHS+toCEdAlNNPnSv1UXV9lChoBkdAbyVXpW3jMmgHS9VoCEdAlNN6nR9gGHV9lChoBkdAcy5mjTKDCmgHS+toCEdAlNO4i9qUNnV9lChoBkdAcralHSWqtGgHTQABaAhHQJTUAeGO+7F1fZQoaAZHQHLT7DqGDcxoB0veaAhHQJTUcg8r7O51fZQoaAZHQG7/LQokRjBoB0vfaAhHQJTUnWXkYGd1fZQoaAZHQHErUc0cfeVoB0vyaAhHQJTU3rxAjY91fZQoaAZHQHMstfkWAPNoB0vcaAhHQJTVtj2Bas91fZQoaAZHQHDE3CXQdCFoB0vTaAhHQJTV6mpEQXh1fZQoaAZHQHHwYjv/io9oB0v1aAhHQJTXNGoaUA11fZQoaAZHQHCFwJTl1bJoB0vOaAhHQJTXe1stTUB1fZQoaAZHQHA01R+BpYdoB0vbaAhHQJTXy2uxKQJ1fZQoaAZHQHAQ1c2R7qpoB0vUaAhHQJTX+gZjx1B1fZQoaAZHQHGUMOG0u15oB0vTaAhHQJTYIIOYplV1fZQoaAZHQHEP0NSZSeloB0vQaAhHQJTYQu3+dbx1fZQoaAZHQHEaDtb9qDdoB0vPaAhHQJTYatZFG5N1fZQoaAZHQHAjJgCwKShoB0vqaAhHQJTYtPacqe91fZQoaAZHQG6HG7rcCYFoB0vPaAhHQJTYtIFvAGl1fZQoaAZHQHN4hNdqtYBoB0vdaAhHQJTZXECNjsl1fZQoaAZHQHMMcd5prUNoB0vnaAhHQJTaRnuiN851fZQoaAZHQHQOV9fCyhVoB0v6aAhHQJTamfJ3gUF1fZQoaAZHQHETElme18doB0vsaAhHQJTasRGtp251fZQoaAZHQHF820iQkopoB0v7aAhHQJTcF4HHFP11fZQoaAZHQHGU/y08eS1oB00AAWgIR0CU3HH8CPp7dX2UKGgGR0BxhjOiWVu8aAdL42gIR0CU3ROWSlnAdX2UKGgGR0BzcZobn5i3aAdL7GgIR0CU3aVsUIszdX2UKGgGR0Bx3iI0qH45aAdLymgIR0CU3btozvZzdX2UKGgGR0Bxl7Sc9W6taAdL6GgIR0CU3hYqXnhbdX2UKGgGR0Bxly9ugpSaaAdL42gIR0CU3ifBeokzdX2UKGgGR0BydCO4oZydaAdL2GgIR0CU3oUn5SFXdX2UKGgGR0BuB9hCtzS1aAdNAAFoCEdAlN6f24/eL3V9lChoBkdAcv/SVnmJWWgHS/FoCEdAlN62uLaVU3V9lChoBkdAcUDQ5FPSD2gHS/9oCEdAlN95TyauwHV9lChoBkdAcws5vcafjGgHS9JoCEdAlN/z3yqdYnV9lChoBkdAbYRKe05U+GgHS9JoCEdAlOBWEPDpDHV9lChoBkdAcwf225QP7WgHTQwBaAhHQJTgfoPkJa91fZQoaAZHQG8K+kYXO4ZoB0vhaAhHQJTgn1SOzY51fZQoaAZHQHKRmuHN5dJoB0vvaAhHQJTiwlSjxkN1fZQoaAZHQHCFygCfYjBoB0vXaAhHQJTjQ/LTx5N1fZQoaAZHQHGZOHi3ocJoB0vdaAhHQJTjg9KVY6p1fZQoaAZHQHPZocNpdrxoB0vVaAhHQJTjnxsl9jR1fZQoaAZHQHE4229cry1oB0vtaAhHQJTkUMgEEDB1fZQoaAZHQG7mDSw4bS9oB0vlaAhHQJTkpjVhCt11fZQoaAZHQHM1qcmShaloB0voaAhHQJTkoysS00F1fZQoaAZHQHJobeyiVSpoB00JAWgIR0CU5XZnctXgdX2UKGgGR0BwhgjzI3iraAdL42gIR0CU5X+WnjyXdX2UKGgGR0Bx/mVopQUIaAdL12gIR0CU5bEzO5avdX2UKGgGR0ByW+1lXiiqaAdLymgIR0CU5eiTt9hJdX2UKGgGR0BynXFXJYDDaAdL1GgIR0CU5kr5ZbIMdWUu"
+    },
+    "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 1024,
+    "gamma": 0.9989918334349422,
+    "gae_lambda": 0.9560281871170067,
+    "ent_coef": 0.0023928414761823316,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 32,
+    "n_epochs": 5,
+    "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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"
+    }
+}

ppo-LunarLander-v2-10/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1212d76b8098d136c1b0be5ab765cdca860d2de7c6226442d8a0b0efe94ab208
+size 88490

ppo-LunarLander-v2-10/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13701618bc54cd859729ff733a0b2338395f2a5af36fed3adf40ae5c2b7c0812
+size 43762

ppo-LunarLander-v2-10/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

ppo-LunarLander-v2-10/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu121
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 273.05766185316986, "std_reward": 21.4472782477192, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-22T20:20:36.068091"}
+{"mean_reward": 277.37517227197634, "std_reward": 31.228445951108668, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-22T21:41:02.033952"}