Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -1402.61 +/- 257.49
+      value: 227.13 +/- 90.97
       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 0x7c9725ee09d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9725ee0a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9725ee0af0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9725ee0b80>", "_build": "<function ActorCriticPolicy._build at 0x7c9725ee0c10>", "forward": "<function ActorCriticPolicy.forward at 0x7c9725ee0ca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9725ee0d30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9725ee0dc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9725ee0e50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9725ee0ee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9725ee0f70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9725ee1000>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9725e7cf40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2000896, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709565032532411298, "learning_rate": 1e-05, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKX9zr7xJl8+Dpo3vhljq7+IMI2/aP+evgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00044800000000000395, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQEBpuDzyz5aMAWyUTegDjAF0lEdAp2MsD0UXYXV9lChoBkfAZ3YizLOiWWgHS4poCEdAp2OMdtEXtXV9lChoBkfAY7Nj81n/UGgHS2VoCEdAp2PVWCEpRXV9lChoBkfAUwJLqUu+RGgHS0BoCEdAp2QAzJp35nV9lChoBkfAZ8u1/DtPYWgHS15oCEdAp2RActGutHV9lChoBkfAXnCSHM2WIGgHS15oCEdAp2SCmygPE3V9lChoBkfAYozwH7gsLGgHS0doCEdAp2SyKR+z+nV9lChoBkfAYOtn9Nvfj2gHS3toCEdAp2UOW4Vh1HV9lChoBkfAajh5ckdFOWgHS2xoCEdAp2VYXZXdTHV9lChoBkfAY1mIacZtN2gHS2ZoCEdAp2W4NiH6/XV9lChoBkfAV30h3aBZp2gHS4FoCEdAp2YwecQRPHV9lChoBkfAYk83iJfplmgHS3doCEdAp2ajlcQiA3V9lChoBkfAar0mmce8w2gHS2VoCEdAp2cCwhW5pnV9lChoBkfAWbALNOdoWmgHS3ZoCEdAp2dzG96C2HV9lChoBkfAUHL5uZThpGgHS11oCEdAp2fCD0163XV9lChoBkfAUYA0XP7emGgHS2loCEdAp2gfqC6H03V9lChoBkfAZ5TS619fC2gHS2NoCEdAp2h59ZzPr3V9lChoBkfAVfnscABDHGgHS0VoCEdAp2i/i1iON3V9lChoBkfAYDAcfeUILWgHS0VoCEdAp2j+a2F36nV9lChoBkfAbYyUY8+zMWgHS3NoCEdAp2mbcM3IdXV9lChoBkfAVLenqFAVwmgHS1doCEdAp2n1fb9IgHV9lChoBkfAXkLTWoWHlGgHS15oCEdAp2o4sf7rLXV9lChoBkfAVAmGgzxgA2gHS1RoCEdAp2pzopx3mnV9lChoBkfAV3KsPrfLtGgHS0ZoCEdAp2qk+5e7c3V9lChoBkfAWFkuez2OAGgHS2VoCEdAp2rqzeGfw3V9lChoBkfARLLZxrBTGmgHS0NoCEdAp2saTW5H3HV9lChoBkfAVWFq33Hq/2gHS2poCEdAp2tjwx33YnV9lChoBkfAUHGQPqcEvGgHS0xoCEdAp2uW9US7G3V9lChoBkfAWowsK9f1H2gHS1VoCEdAp2vQjUutfXV9lChoBkfAT6yLZSNwSGgHS1VoCEdAp2wJ+UhV2nV9lChoBkfAXmakTHsC1mgHS1RoCEdAp2xH+IdlunV9lChoBkfAZMNOvdM0xmgHS1poCEdAp2ygG0NSZXV9lChoBkfAUhfcM3IdVGgHS0RoCEdAp2zPLcKw6nV9lChoBkfAYM+mjTKDCmgHS3xoCEdAp20mbAk9lnV9lChoBkfAVV38XN1QqWgHS2RoCEdAp21r/4qPO3V9lChoBkfAYXdru6VdHGgHS2loCEdAp22ywbEP2HV9lChoBkfAUrLYdyT6i2gHS0poCEdAp23kCPp6hXV9lChoBkfAWlF40Mw1zmgHS0xoCEdAp24X+fh/AnV9lChoBkfAVQKyTpxFRmgHS0xoCEdAp25OQhfShXV9lChoBkfAVPyuV5a/y2gHS0loCEdAp26AuM+/xnV9lChoBkfAUcUvzvqkdmgHS1toCEdAp26/qHGjsXV9lChoBkfATtGlwcYIjWgHS1FoCEdAp274Ap8WsXV9lChoBkfAXny6iCaqj2gHS1RoCEdAp28yhtcfNnV9lChoBkfAcNvYR/ViF2gHS4doCEdAp2+nC9AX23V9lChoBkfAXdwXZXdTHmgHS2NoCEdAp2/qMxXXAnV9lChoBkfAYKHl9Sde6mgHS1loCEdAp3Aok7fYSXV9lChoBkfAQOjxb0OEumgHS2loCEdAp3By4OMER3V9lChoBkfAcJyfSQYDT2gHS3RoCEdAp3DBi7TUiXV9lChoBkfAYRO3qiXY2GgHS1hoCEdAp3EDjtG/e3V9lChoBkfAVgidTYNAkmgHS0doCEdAp3E2mR/3FnV9lChoBkfAXEhGUfPom2gHS1poCEdAp3F5XXAdn3V9lChoBkfAUoIiPhhpg2gHS2hoCEdAp3G/j81n/XV9lChoBkfAQ61JjDsMRmgHS4ZoCEdAp3IasuFpPHV9lChoBkfAUWuu8scyWWgHS1BoCEdAp3JzXe3x4XV9lChoBkfAVZ3cVQAMlWgHS1NoCEdAp3KwgzP8h3V9lChoBkfAVVvPomoitGgHS0poCEdAp3Llh3JPqXV9lChoBkfAWMdSaVlf7mgHS1RoCEdAp3MhnrY5DXV9lChoBkfAZSpES/TLGWgHS45oCEdAp3OF/SYw7HV9lChoBkfAPnVGb1AZ9GgHS3RoCEdAp3PZOpKjBXV9lChoBkfAcOzy/KyOaWgHS4FoCEdAp3QylYU343V9lChoBkfAbHgLtNSIg2gHS2toCEdAp3SCXMQmNXV9lChoBkfAXJLSApazNWgHS11oCEdAp3TEZBLPEHV9lChoBkfAcMwFfiPyTmgHS2loCEdAp3UPpt78enV9lChoBkfAZbW3mV7hN2gHS71oCEdAp3Wq72+PBHV9lChoBkfAWHz8HfMwDmgHS1doCEdAp3XlajesP3V9lChoBkfAVj3CN0eU6mgHS1hoCEdAp3YhNsWO63V9lChoBkfAWTypYLb5/WgHS5BoCEdAp3aKAtnPFHV9lChoBkfAVLMh3aBZp2gHS0toCEdAp3a9F2FFlXV9lChoBkfAYLVDqGDcumgHS1hoCEdAp3b5b6guiHV9lChoBkfAXdeiyprDZWgHS1JoCEdAp3cyEFnqV3V9lChoBkfAVM/5N47ihmgHS0xoCEdAp3dkV8CxNnV9lChoBkfAVuKYsunMuGgHS31oCEdAp3e3dM0xd3V9lChoBkfAUs18IAwPAmgHS0hoCEdAp3fnSjQAuXV9lChoBkfAYmIW5Yoy9GgHS3BoCEdAp3hNFz+3pnV9lChoBkfAVJ2COFQEZGgHS1NoCEdAp3iK4MF2V3V9lChoBkfAb9TUUfxMFmgHS49oCEdAp3jxk9U0enV9lChoBkfAYFGxGlQ/HGgHS3doCEdAp3lEdV/+bXV9lChoBkfAVwCtlqagEmgHS31oCEdAp3mZbdJrcnV9lChoBkfAYDBQSBbwB2gHS3hoCEdAp3nqgVXV9XV9lChoBkfAXcEMvysjmmgHS3RoCEdAp3o5WxQizXV9lChoBkfAZR68OkLx7WgHS3loCEdAp3qQpH7P6nV9lChoBkfAT7hpWV/tpmgHSzxoCEdAp3q6R+z+m3V9lChoBkfAbaXda+vhZWgHS3xoCEdAp3ssIJJGv3V9lChoBkfAU0tgKF7D22gHS11oCEdAp3ttxEORT3V9lChoBkfAae+f6oESumgHS2ZoCEdAp3u70J4SpXV9lChoBkfAcn/UypJf6WgHS5FoCEdAp3wgoCuEEnV9lChoBkfAUSVGtp22X2gHS0RoCEdAp3xRV+7UX3V9lChoBkfAT1xeb/ffoGgHS3poCEdAp3ys/wAlwHV9lChoBkfAaZsggX/HYGgHS4poCEdAp30TONYKY3V9lChoBkfAUb+kO7QLNWgHS4VoCEdAp31yef7Jn3V9lChoBkfAacYW69TP0WgHS4poCEdAp33RxvNu+HV9lChoBkfAVGNd5Y5ksmgHS2xoCEdAp35VmUW2w3V9lChoBkfAYZpcqOLiuWgHS0toCEdAp36iYTj//HV9lChoBkfAcGp0oScslWgHS4JoCEdAp38VLzwtrnV9lChoBkfAdbxP+4smOWgHS15oCEdAp39oH5aePXV9lChoBkfAV6A1KoQ4CWgHS1hoCEdAp3+yXt0FKXV9lChoBkfAXtwbdadMCmgHS4VoCEdAp4Af7WNFSnV9lChoBkfAY8voYekpJGgHS3poCEdAp4CQZ/CqInV9lChoBkfAYES/lhgE2mgHS3hoCEdAp4EE87p3YHV9lChoBkfAUTZ7pmmLtWgHS1BoCEdAp4FXbdrO7nVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7816, "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": 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": 512, "n_epochs": 4, "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-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 0x7debae25b640>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7debae25b6d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7debae25b760>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7debae25b7f0>", "_build": "<function ActorCriticPolicy._build at 0x7debae25b880>", "forward": "<function ActorCriticPolicy.forward at 0x7debae25b910>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7debae25b9a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7debae25ba30>", "_predict": "<function ActorCriticPolicy._predict at 0x7debae25bac0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7debae25bb50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7debae25bbe0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7debae25bc70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7debae206bc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2000896, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709570152267121141, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGYcUT2Pfme6h0Yns/nzM6/Xqic6DuzIMwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00044800000000000395, "_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": 7816, "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": 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:": "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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": "False", "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 sha256:1c8bb944ee3c399314244c78914e9d6e8e455a768326dce270c6f9c14b3f47d2
-size 147298
+oid sha256:3ad9e3ea8388b59777c2851e5ad5dafd7cef318261d2a0f03d8749f699761c19
+size 146827

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7c9725ee09d0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9725ee0a60>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c9725ee0af0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9725ee0b80>",
-        "_build": "<function ActorCriticPolicy._build at 0x7c9725ee0c10>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7c9725ee0ca0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9725ee0d30>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9725ee0dc0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7c9725ee0e50>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9725ee0ee0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9725ee0f70>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9725ee1000>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7debae25b640>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7debae25b6d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7debae25b760>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7debae25b7f0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7debae25b880>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7debae25b910>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7debae25b9a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7debae25ba30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7debae25bac0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7debae25bb50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7debae25bbe0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7debae25bc70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c9725e7cf40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7debae206bc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1709565032532411298,
-    "learning_rate": 1e-05,
+    "start_time": 1709570152267121141,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKX9zr7xJl8+Dpo3vhljq7+IMI2/aP+evgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGYcUT2Pfme6h0Yns/nzM6/Xqic6DuzIMwAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_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'>",
@@ -83,7 +83,7 @@
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 512,
+    "batch_size": 64,
     "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
@@ -94,6 +94,6 @@
     "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:e87af1616e73f72aca722fa93f9b07163b2833cf90f620db2f3d4beb100943cf
-size 88362
+oid sha256:989718519027c9347a1900a15936e78ec922a69111258d89e3f9055176b924ac
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf831eb6b3ef7bb1aa0389976347f82bb906aa1b876b213dc3fe040d069d18b8
-size 43762
+oid sha256:85ecd8d9ad9fdda5f5f78e0257f21b56704a941c004196421eaa5e48bc9de15f
+size 43634

ppo-LunarLander-v2/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.1.0+cu121
-- GPU Enabled: True
+- GPU Enabled: False
 - Numpy: 1.25.2
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1

results.json

@@ -1 +1 @@
-{"mean_reward": -1402.6076093, "std_reward": 257.4918642655671, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T16:03:12.052103"}
+{"mean_reward": 227.1348861, "std_reward": 90.96873070671982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T17:16:44.882659"}