first model version

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -457.23 +/- 48.56
+      value: 53.75 +/- 148.84
       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 0x7efe32929870>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efe32929900>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efe32929990>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efe32929a20>", "_build": "<function ActorCriticPolicy._build at 0x7efe32929ab0>", "forward": "<function ActorCriticPolicy.forward at 0x7efe32929b40>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efe32929bd0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efe32929c60>", "_predict": "<function ActorCriticPolicy._predict at 0x7efe32929cf0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efe32929d80>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efe32929e10>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efe32929ea0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7efdeaed4040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1024, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684101427327165418, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAG0Xcj7rQ9I/ZfQFP36C5L0bHz++9yA9vgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVVAEAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwGkRhAnlXBCMAWyUS1WMAXSUR0BQepobn5i3dX2UKGgGR8BdV0lzEJjUaAdLc2gIR0BQhe9Ba9sadX2UKGgGR8Bi2tPN3W4FaAdLSmgIR0BQjUTtb9qDdX2UKGgGR8Bdw+LR8c+8aAdLgWgIR0BQmiUs4DLbdX2UKGgGR8B40OQjlgc+aAdLgGgIR0BQp05U96kZdX2UKGgGR8BZ3sA7xNItaAdLaWgIR0BQsVBIFvAHdX2UKGgGR8BadsOXmeUZaAdLQmgIR0BQt+LiuMdcdX2UKGgGR8BzrKs5n13/aAdLZWgIR0BQwjk+5e7ddX2UKGgGR8B2/qZw4sEraAdLWmgIR0BQy8O09hZydX2UKGgGR8BZzUeEIw/QaAdLUGgIR0BQ2FF2FFlTdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "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": 1, "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, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7ffa59379090>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffa59379120>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffa593791b0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffa59379240>", "_build": "<function ActorCriticPolicy._build at 0x7ffa593792d0>", "forward": "<function ActorCriticPolicy.forward at 0x7ffa59379360>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffa593793f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffa59379480>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffa59379510>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffa593795a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffa59379630>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffa593796c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffa0407b580>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1684159702447446769, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALPTib6WtzU/mWoqvuO0Qb7hZ1a83TIzvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0014719999999999178, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGudpJPIn0GMAWyUTdgBjAF0lEdApCU1nEl3QnV9lChoBkdAYjDmK64DtGgHTVACaAhHQKQnmpLmITJ1fZQoaAZHQGgUeU6gdwNoB03EAWgIR0CkKYgUUO/ddX2UKGgGR0BtQ1UKiO/+aAdNyAFoCEdApC3vNeMQ3HV9lChoBkdAb0usEJSiumgHTf0BaAhHQKQvWRsdkrh1fZQoaAZHwFJnljVhCt1oB02iAWgIR0CkMH/HPu5SdX2UKGgGR0BGfJ7sv7FbaAdN6ANoCEdApDX2H+Idl3V9lChoBkfAShr3j+717WgHTXsBaAhHQKQ2/d/rjYJ1fZQoaAZHQDtI72criERoB03oA2gIR0CkOcs9B8hLdX2UKGgGR0BhOeqaPS2IaAdNogJoCEdApD5fO8kD6nV9lChoBkdAXhqaBqbjLmgHTcQCaAhHQKRAx4nF5v91fZQoaAZHQFIJY1He7+VoB03oA2gIR0CkRLBUaQ3hdX2UKGgGR0BjA5Qgs9SuaAdN3wFoCEdApEnX1Hvtt3V9lChoBkdAbFY+7Dl5nmgHTecBaAhHQKRLONEw35x1fZQoaAZHQG7r/A9FF2FoB02wAWgIR0CkTHbiyY5UdX2UKGgGR0BgiGN1hb4baAdNNwJoCEdApE4OJDVpbnV9lChoBkdAWYzronrpq2gHTbICaAhHQKRSzVfeDWd1fZQoaAZHQFhzyy2QXANoB03oA2gIR0CkVbLPt2LYdX2UKGgGR0A/AVbRnezlaAdN6ANoCEdApFs5R0lqrXV9lChoBkdAbUwXzlLeymgHTdIBaAhHQKRcwGxD9fl1fZQoaAZHQGfWahQFcIJoB03NAWgIR0CkXnZTho/SdX2UKGgGR0BlEOPzWf9QaAdN3wFoCEdApGBAQOFxn3V9lChoBkfAXTo04zabnWgHTeUBaAhHQKRl++iaiK11fZQoaAZHQE5rb9If8uVoB03oA2gIR0CkaNm65Gz9dX2UKGgGR0BwRIpw0fozaAdNowFoCEdApGoKTUy57XV9lChoBkfAVBkPQOWjXWgHTf0BaAhHQKRre4yXUpd1fZQoaAZHQGxtKpcX3xpoB03QAWgIR0Ckb30Q9RrKdX2UKGgGR0Bi/bY5DJEIaAdNKAJoCEdApHEMlkYoAnV9lChoBkdAbWanBtUGV2gHTdoBaAhHQKRyYtEofCB1fZQoaAZHQG2wxYzSCvpoB035AWgIR0Ckc9ZpBX0YdX2UKGgGR0BBljkdV/+baAdN6ANoCEdApHmCz1K5CnV9lChoBkdAZvw2l2vB8GgHTdwBaAhHQKR7Rszl90B1fZQoaAZHQGebQQ176YVoB03cAWgIR0CkfRlgUlAvdX2UKGgGR0BROzWbwz+FaAdN6ANoCEdApIR6c9W6snV9lChoBkdAZeMgsbvPT2gHTQ8CaAhHQKSF80dBBzF1fZQoaAZHwCEN2mpEQXhoB02CAWgIR0CkhwUzj3mFdX2UKGgGR0Beji83++/QaAdNuwJoCEdApIux7mdRSHV9lChoBkfAUIisFMZgomgHTZEBaAhHQKSM1wjt5Ut1fZQoaAZHQGp3jXnQpnZoB03LAWgIR0CkjilMyrPudX2UKGgGR0BsPp95Qgs9aAdN0gFoCEdApI90B+4LC3V9lChoBkdAbO+O4oZydWgHTbkBaAhHQKSTYuSwGGF1fZQoaAZHQGzOoN/e+EhoB01MA2gIR0Ckld13t8eCdX2UKGgGR0Bh0LiIcinpaAdNRwJoCEdApJfZWxQizXV9lChoBkdAboFFPSDyv2gHTdwBaAhHQKSZqYht+Ct1fZQoaAZHQGnN8inpB5ZoB03mAWgIR0Ckn8n4wh4ddX2UKGgGR8A1F0D2alUIaAdN6ANoCEdApKKvbj94vHV9lChoBkdAXGMmzByjpWgHTSACaAhHQKSkQUaAFxJ1fZQoaAZHQFVEFz+3pfRoB03oA2gIR0Ckqe3m3fALdX2UKGgGR0Bvmw/RmbsoaAdNwQFoCEdApKs1/WlMy3V9lChoBkdAXTEl8gIQe2gHTdkCaAhHQKSwCyB06o51fZQoaAZHQG0nLteD3/RoB03cAWgIR0CksWeglF+edX2UKGgGR0BnyxL26ClKaAdN1wFoCEdApLK8RSP2f3V9lChoBkdAYS7D+BH09WgHTUECaAhHQKS0eTW5H3F1fZQoaAZHQHBX1gx8D0VoB030AWgIR0CkuhtiYsundX2UKGgGR0BbcX2IwdsBaAdNHwJoCEdApLxutITXa3V9lChoBkdAW8wTDfm9x2gHTUMCaAhHQKS+aI0IkZ91fZQoaAZHQEOKoLG7z09oB02NAWgIR0Ckv4Vog3cYdX2UKGgGR0Bt2+MfigkDaAdNvwFoCEdApMDaeXiR4nV9lChoBkdAZfqdLg4wRGgHTaECaAhHQKTFhLFn7Hh1fZQoaAZHwEujpwjt5UtoB028AWgIR0CkxscSwnpjdX2UKGgGR0BTpSowVTJhaAdN6ANoCEdApMxr8R+SbHV9lChoBkfAYCghnrY5DWgHTSYCaAhHQKTOB7b+Lm91fZQoaAZHwFK79VWCEpRoB03VAWgIR0Ckz1XK0UoKdX2UKGgGR8BAsBk7OmiyaAdNiQFoCEdApNB0chkiEHV9lChoBkfAVfDIgeRxLmgHTaQBaAhHQKTRtst03fh1fZQoaAZHwFkTGKAJ9iNoB01OAmgIR0Ck17jzyz5XdX2UKGgGR0Bnzj5dnkDIaAdN2gFoCEdApNm7jLjgh3V9lChoBkdAa5+l/H5rQGgHTbgBaAhHQKTbQVXV9Wp1fZQoaAZHQFuonbItDlZoB03HAmgIR0Ck3UjGDL8rdX2UKGgGR0Bu+NfCyhSMaAdNjgFoCEdApOEStxMnJHV9lChoBkdAbXH+yZ8a42gHTd0BaAhHQKTia03wTdt1fZQoaAZHQGi5YjB2wFFoB03yAWgIR0Ck488uJ1q4dX2UKGgGR0BnWi4UeuFIaAdNxAFoCEdApOUeYplSTHV9lChoBkdAbsiFi8WbgGgHTeQBaAhHQKTpSM+/xlR1fZQoaAZHQGtN8qnWJ79oB03EAWgIR0Ck6qVanrIHdX2UKGgGR0Bk4J6po9LYaAdNJQJoCEdApOxG/rSmZXV9lChoBkdAZVfI8QqZt2gHTf4BaAhHQKTtvjXnQpp1fZQoaAZHQFAMURWcSXdoB03oA2gIR0Ck9XrbxmTUdX2UKGgGR0BjeiuGKyfMaAdNxgFoCEdApPdqr7waznV9lChoBkdAYD3+yZ8a42gHTQYDaAhHQKT57n7Hhjx1fZQoaAZHQFcCPv8ZUDNoB03oA2gIR0Ck/5hFEy+IdX2UKGgGR0BhAVY0VJtjaAdNXwJoCEdApQFfStvGZXV9lChoBkdAY9eNOuaF22gHTdgDaAhHQKUHKL9deIF1fZQoaAZHQFF06vaDf3xoB03oA2gIR0ClCi43FUADdX2UKGgGR0BgSGIhyKekaAdNYQJoCEdApQv5vaURnXV9lChoBkdAa7bLW7OE/WgHTUYCaAhHQKUR+7rcCYF1fZQoaAZHQGIo3NTtLL9oB00jAmgIR0ClFFIHC4z8dX2UKGgGR0BvTR3V09yMaAdNrQFoCEdApRYXUnXumnV9lChoBkdAbb6puMuOCGgHTfcBaAhHQKUXlO6/Zdx1fZQoaAZHQGpMrhJiAlRoB03eAWgIR0ClG+AyVObidX2UKGgGR0Aorpkf9xZMaAdNiwFoCEdApR0Kf16E8XV9lChoBkdAaSjdtVJcxGgHTfsBaAhHQKUegtfXwsp1fZQoaAZHQGmsXTd+G49oB03pAWgIR0ClH/lT3qRmdX2UKGgGR0BvD9mBe5WjaAdNwAFoCEdApSQtLSNOunV9lChoBkfASe14X40uUWgHTeoBaAhHQKUlnfYzzmR1fZQoaAZHQGO55WaMJhRoB00VAmgIR0ClJyOtfXwtdX2UKGgGR0BlpcZ3s5XEaAdN9AFoCEdApSiSLCN0eXV9lChoBkdAY8tDqGDcumgHTf8CaAhHQKUu0WgOBlN1fZQoaAZHQGI7jW9US7JoB000A2gIR0ClMk1Oj7AMdX2UKGgGR0Bl+b850bLmaAdNDwJoCEdApTQNr2xptnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5870, "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": 1, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 sha256:69cb213ef9575d2045e7a70d3e22c106be61b492ee97320600e0ec67178ffefb
-size 142353
+oid sha256:a704facb09b012a34e2ab0c60652468448b642fad370c5b7801d9bf8233b3a9d
+size 146099

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 0x7efe32929870>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efe32929900>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efe32929990>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efe32929a20>",
-        "_build": "<function ActorCriticPolicy._build at 0x7efe32929ab0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7efe32929b40>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7efe32929bd0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efe32929c60>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7efe32929cf0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efe32929d80>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efe32929e10>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efe32929ea0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ffa59379090>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffa59379120>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffa593791b0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffa59379240>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ffa593792d0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ffa59379360>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffa593793f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffa59379480>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ffa59379510>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffa593795a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffa59379630>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffa593796c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7efdeaed4040>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ffa0407b580>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1024,
-    "_total_timesteps": 1000,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1684101427327165418,
+    "start_time": 1684159702447446769,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAG0Xcj7rQ9I/ZfQFP36C5L0bHz++9yA9vgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAALPTib6WtzU/mWoqvuO0Qb7hZ1a83TIzvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.02400000000000002,
+    "_current_progress_remaining": -0.0014719999999999178,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVVAEAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwGkRhAnlXBCMAWyUS1WMAXSUR0BQepobn5i3dX2UKGgGR8BdV0lzEJjUaAdLc2gIR0BQhe9Ba9sadX2UKGgGR8Bi2tPN3W4FaAdLSmgIR0BQjUTtb9qDdX2UKGgGR8Bdw+LR8c+8aAdLgWgIR0BQmiUs4DLbdX2UKGgGR8B40OQjlgc+aAdLgGgIR0BQp05U96kZdX2UKGgGR8BZ3sA7xNItaAdLaWgIR0BQsVBIFvAHdX2UKGgGR8BadsOXmeUZaAdLQmgIR0BQt+LiuMdcdX2UKGgGR8BzrKs5n13/aAdLZWgIR0BQwjk+5e7ddX2UKGgGR8B2/qZw4sEraAdLWmgIR0BQy8O09hZydX2UKGgGR8BZzUeEIw/QaAdLUGgIR0BQ2FF2FFlTdWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 4,
+    "_n_updates": 5870,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -77,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "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": 4,
+    "n_epochs": 10,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d75874e348dddf60b5961d3cd280e2d3f396b703313681a334a85e56610bdf9
+oid sha256:8458946171706116d5f03aeb0e47aeaedfc59bf3d7a220c752f86c2f85d92b1b
 size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235c43bd84bb29577cf464a4ec76e65733a1018de1625864e99f89d38bcf03cd
+oid sha256:ddc0dfdc177e029e1dfacdf7e5b53d30e43700fcd4a98778b95891f32dc9554a
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": -457.23151009939613, "std_reward": 48.55522679952396, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-14T22:17:29.412789"}
+{"mean_reward": 53.75154299061901, "std_reward": 148.8426300477246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-15T14:53:55.712914"}