Increase number of steps and upload trained agent using PPO on LunarLander-v2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 259.12 +/- 21.34
+      value: 281.32 +/- 22.35
       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 0x7b5fcbe01000>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b5fcbe01090>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b5fcbe01120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b5fcbe011b0>", "_build": "<function ActorCriticPolicy._build at 0x7b5fcbe01240>", "forward": "<function ActorCriticPolicy.forward at 0x7b5fcbe012d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b5fcbe01360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b5fcbe013f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7b5fcbe01480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b5fcbe01510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b5fcbe015a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b5fcbe01630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b5fcbdaa0c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710262090139389310, "learning_rate": 0.0, "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": 291, "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/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "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": "1.25.2", "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 0x7d2899a48820>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2899a488b0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2899a48940>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2899a489d0>", "_build": "<function ActorCriticPolicy._build at 0x7d2899a48a60>", "forward": "<function ActorCriticPolicy.forward at 0x7d2899a48af0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2899a48b80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2899a48c10>", "_predict": "<function ActorCriticPolicy._predict at 0x7d2899a48ca0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2899a48d30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2899a48dc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2899a48e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d2899a4c680>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710265788728443277, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV5AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHI7VYU34sWMAWyUS/SMAXSUR0Cj/1XF98Z2dX2UKGgGR0ByWZbFCLMtaAdLxWgIR0Cj/2At4A0bdX2UKGgGR0BxJeQ/5ckdaAdLzmgIR0Cj/2MlTm4idX2UKGgGR0ByYtWkrPMTaAdLumgIR0Cj/3CK77KrdX2UKGgGR0BzrofRu0kXaAdL7GgIR0Cj/3VCgK4QdX2UKGgGR0Bx+DUXpGF0aAdL22gIR0Cj/+YTsY2sdX2UKGgGR0B0DLWUbDMvaAdL0WgIR0CkACyteUpvdX2UKGgGR0BzFqYRdyDJaAdL02gIR0CkAE6AnUlSdX2UKGgGR0ByO1TUAks0aAdLxWgIR0CkAGHNxEORdX2UKGgGR0ByGojmjj7zaAdLsWgIR0CkAIOez2OAdX2UKGgGR0Bx9WQuEmICaAdLxmgIR0CkAKa+36RAdX2UKGgGR0BxziagElmfaAdLwGgIR0CkAKf9P1tgdX2UKGgGR0BwtwdBBzFNaAdL1GgIR0CkAKudwvQGdX2UKGgGR0Bw93kQwsXjaAdLwmgIR0CkAOaC17Y1dX2UKGgGR0BwYnCvX9R8aAdL3GgIR0CkARsKTjebdX2UKGgGR0BybaL5ylvZaAdL0mgIR0CkASFotcv/dX2UKGgGR0Btvy5mRNh3aAdLvmgIR0CkAT2gWac7dX2UKGgGR0BywrUoa1kUaAdLuWgIR0CkAUmbb1yvdX2UKGgGR0BxPsA/9pAVaAdLwGgIR0CkAUrrxAjZdX2UKGgGR0Bz/JiCrcTKaAdLxWgIR0CkAVjbrTpgdX2UKGgGR0BvsPfAKv3baAdLv2gIR0CkAVyE12q2dX2UKGgGR0Byh3WXkYGdaAdLuWgIR0CkAgtcOby6dX2UKGgGR0BxoI3EQ5FPaAdL52gIR0CkGMrZJ04jdX2UKGgGR0ByARt8/lhgaAdLs2gIR0CkGQXenAIqdX2UKGgGR0By+G9pRGc4aAdLzGgIR0CkGQShakhzdX2UKGgGR0Bxz3ND+irUaAdLy2gIR0CkGSbjLjgidX2UKGgGR0Bx6eG/N7jUaAdL5WgIR0CkGTbhegL7dX2UKGgGR0Bxd+C04R29aAdLy2gIR0CkGU6mXPZ7dX2UKGgGR0ByQnTiKiwjaAdLz2gIR0CkGVYxtYSydX2UKGgGR0Bx4v4wh4dIaAdLsGgIR0CkGYLrX18LdX2UKGgGR0BzHGe6I3zdaAdLvmgIR0CkGco9cKPXdX2UKGgGR0Bxz5s0pEx7aAdLwWgIR0CkGd/yPMjedX2UKGgGR0B0CrGlyimEaAdLvmgIR0CkGe3BP9DQdX2UKGgGR0BzA51Tzd1uaAdLyWgIR0CkGfexwAEMdX2UKGgGR0BwzkN/e+EiaAdLsmgIR0CkGpLHlwLmdX2UKGgGR0By/EQYk3S8aAdNJgFoCEdApBrdtO2y9nV9lChoBkdAcalkRzzVc2gHS8ZoCEdApBsQ9cKPXHV9lChoBkdAcROMbm2b5WgHS71oCEdApBtjVUdaMnV9lChoBkdAcTw3PRiPQ2gHS69oCEdApBtnqZ+hG3V9lChoBkdAcijMG5c1O2gHS7xoCEdApBt1uHerMnV9lChoBkdAdHH9jgAIY2gHTT4BaAhHQKQbhV3ljmV1fZQoaAZHQHEqUQoTfzloB0vSaAhHQKQbhK5kK/p1fZQoaAZHQHFtiXUpd8loB0u/aAhHQKQboxbjcVR1fZQoaAZHQHBwEOVgQYloB02JAWgIR0CkG97/Ot4idX2UKGgGR0Bycc6/7BO6aAdLq2gIR0CkG/h+F10UdX2UKGgGR0Bw69BnjABUaAdL1GgIR0CkHBBJAdGRdX2UKGgGR0By4lpGnXNDaAdL2WgIR0CkHGPn0TURdX2UKGgGR0ByxjD4xk/baAdL1WgIR0CkHHqWC2+gdX2UKGgGR0Byi5me18b8aAdL22gIR0CkHJOz6ab4dX2UKGgGR0BySR+UhV2iaAdLtGgIR0CkHLQmmce9dX2UKGgGR0By50NWluWKaAdLsWgIR0CkHOr9MsYmdX2UKGgGR0BzM/dgv115aAdLyWgIR0CkHVh0p3HJdX2UKGgGR0BzOzN0NjLCaAdLvGgIR0CkHXd0aIepdX2UKGgGR0Bu6AEZBLPEaAdLvGgIR0CkHYSq+8GtdX2UKGgGR0BuIHsu3+dcaAdLxGgIR0CkHai83++/dX2UKGgGR0Byxzv/io87aAdLxmgIR0CkHa4pMHrydX2UKGgGR0BzEbrTpgTiaAdL0mgIR0CkHbZR0lqrdX2UKGgGR0Bxf6AlOXVtaAdLwGgIR0CkHbjtXxOMdX2UKGgGR0BydK/h2nsLaAdLuGgIR0CkHgoldC3PdX2UKGgGR0By8RvGZNO/aAdLymgIR0CkHircCYCydX2UKGgGR0B0AsdxQzk7aAdL3WgIR0CkHkWgezUrdX2UKGgGR0BxeACDEm6YaAdLvGgIR0CkHqIIOYpldX2UKGgGR0BxBbXiBGx2aAdL2mgIR0CkHsVMmF8HdX2UKGgGR0Bz73Ue+23KaAdLwmgIR0CkHtkGzKLbdX2UKGgGR0BxF65z5oGqaAdL4mgIR0CkHvROclPadX2UKGgGR0BzFZsuWa+faAdLwWgIR0CkHw28IzFddX2UKGgGR0ByaFkJ8fFKaAdLumgIR0CkH4Tuv2XcdX2UKGgGR0ByL/wTdtVJaAdLuWgIR0CkH4+sYEW7dX2UKGgGR0Bx6HkDIRywaAdL2mgIR0CkH8PkRzzVdX2UKGgGR0ByScGFBY3eaAdLwWgIR0CkH8vJRwZPdX2UKGgGR0By2+pLmITHaAdLv2gIR0CkH8qmsNlRdX2UKGgGR0ByuHhwVCXyaAdLu2gIR0CkH8rE9+w1dX2UKGgGR0ByIr6YVqN7aAdLy2gIR0CkH/CswL3LdX2UKGgGR0Bx8QCRwIdEaAdLrWgIR0CkIA5J04ipdX2UKGgGR0BvzwvcrRShaAdLzWgIR0CkIG5wn6VMdX2UKGgGR0Buxea2F36iaAdLyGgIR0CkIKcTakAQdX2UKGgGR0BzFSSQo1DTaAdNqwJoCEdApCD4zeoDPnV9lChoBkdAca5NmDlHSWgHS75oCEdApCD8vK2a2HV9lChoBkdAcRypLEk0JmgHS7poCEdApCEY2ZRbbHV9lChoBkdAcRu46Oo5xWgHS8NoCEdApCGb/sE7n3V9lChoBkdAcsFvgFX7tWgHS9xoCEdApCGz3RG+bnV9lChoBkdAc7bDPGACn2gHS+RoCEdApCHxfWtlqnV9lChoBkdAcg0oh6jWTWgHS7NoCEdApCJa6UaAF3V9lChoBkdAc7wRrrPdEmgHS9NoCEdApCJ8X+ERJ3V9lChoBkdAcPVUb1h9cGgHS8poCEdApCKtEgGKRHV9lChoBkdAc0etDUmUn2gHS99oCEdApCK6HoHLR3V9lChoBkdAc48r4WUKRmgHS7xoCEdApCLmGM4tH3V9lChoBkdAc3fqxkd3jmgHS9ZoCEdApCLphScbznV9lChoBkdAcGNcVxjriWgHS8poCEdApCLxWDHwPXV9lChoBkdAckzkcS5AhWgHS95oCEdApCMClzltCXV9lChoBkdAcDQbVz6rNmgHS8poCEdApCNg8r7O3XV9lChoBkdAcGlZEUj9oGgHS7doCEdApCOdY0VJtnV9lChoBkdAcQhqT8pCr2gHS8JoCEdApCPNIy0rsnV9lChoBkdAc6yco6S1V2gHS9xoCEdApCPaJXQtz3V9lChoBkdAcTmiO/+Kj2gHS8VoCEdApCP3z19ORHV9lChoBkdAcseqOLiuMmgHS8NoCEdApCRkf5k9U3V9lChoBkdAcPvbcGkeqGgHS8doCEdApCSADNhVl3V9lChoBkdAcN2yVv/BFmgHS6doCEdApCSg/Z/Tb3V9lChoBkdAc16vhIe5nWgHS8RoCEdApCSmpEQXh3V9lChoBkdANGNIK+i8F2gHS4ZoCEdApCUBGvwEyXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1230, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "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-6.1.58+-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": "1.25.2", "Cloudpickle": "2.2.1", "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:d615a9cce5978e06c9809330311453838bd02051b59ce5e8843c5ae4a713e945
-size 147909
+oid sha256:e09c857079d4cd62d45652424c5bebd60fd1cfcd7509c347737fb618d4724b9b
+size 147962

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7b5fcbe01000>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b5fcbe01090>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b5fcbe01120>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b5fcbe011b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b5fcbe01240>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b5fcbe012d0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b5fcbe01360>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b5fcbe013f0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b5fcbe01480>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b5fcbe01510>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b5fcbe015a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b5fcbe01630>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d2899a48820>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d2899a488b0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d2899a48940>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d2899a489d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d2899a48a60>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d2899a48af0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d2899a48b80>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d2899a48c10>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d2899a48ca0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d2899a48d30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d2899a48dc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d2899a48e50>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b5fcbdaa0c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d2899a4c680>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 2015232,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1710262090139389310,
-    "learning_rate": 0.0,
+    "start_time": 1710265788728443277,
+    "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'>",
@@ -41,32 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": -0.007616000000000067,
     "_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": 291,
-    "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,
+    "_n_updates": 1230,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -84,7 +69,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -92,8 +77,23 @@
         "_np_random": null
     },
     "n_envs": 16,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "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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"
+        ":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:a8fbaa1284ee2d6d00c46e91f4370f747c14a41d754c35858f549d15f7adba8a
-size 88490
+oid sha256:257f8b636ca54931dd1c8b70565f0c2c7da79306f22e0b09e49194b47855fb82
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cc578d12eb31570f07aeb5e483d64b3d2565f429d1ca99bd44334189a24020
+oid sha256:048802b39a3abf794179b82cc3f06a9fbbf4ab89302a8287ce10317afa8b8746
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 259.1244306, "std_reward": 21.338845756469492, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-12T17:30:21.869030"}
+{"mean_reward": 281.3173381, "std_reward": 22.353072878967755, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-12T18:30:51.850846"}