Adding::Bipedal Walker trained using PPO

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: 229.21 +/- 63.57
+      value: 209.63 +/- 82.30
       name: mean_reward
       verified: false
 ---

bipedal_walker_10m.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46711739cb5ae1c4562ba437e1c5926e8eeeafa39d1ca6c98d8a9a65ada12076
+oid sha256:553d0fe754495fbc8ffbd040fa6ebd46fe1843c839f509dd71794f86ee7d3cc9
 size 173306

bipedal_walker_10m/data

@@ -4,19 +4,19 @@
         ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fdcfd1cb5b0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdcfd1cb640>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdcfd1cb6d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdcfd1cb760>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fdcfd1cb7f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fdcfd1cb880>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdcfd1cb910>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fdcfd1cb9a0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdcfd1cba30>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdcfd1cbac0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdcfd1cbb50>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f57120cf5b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57120cf640>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57120cf6d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57120cf760>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f57120cf7f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f57120cf880>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57120cf910>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f57120cf9a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57120cfa30>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57120cfac0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57120cfb50>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fdcfd1d4540>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f57120c7b80>"
     },
     "verbose": 1,
     "policy_kwargs": {},

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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7fdcfd1cb5b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fdcfd1cb640>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fdcfd1cb6d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fdcfd1cb760>", "_build": "<function ActorCriticPolicy._build at 0x7fdcfd1cb7f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fdcfd1cb880>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fdcfd1cb910>", "_predict": "<function ActorCriticPolicy._predict at 0x7fdcfd1cb9a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fdcfd1cba30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fdcfd1cbac0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fdcfd1cbb50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fdcfd1d4540>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [24], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "n_envs": 1, "num_timesteps": 10009600, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671097329495755806, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.0009600000000000719, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVfhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIWOTXD7G5aUCUhpRSlIwBbJRNtgWMAXSUR0C3hPoa1kUcdX2UKGgGaAloD0MIK/aX3ZNEXsCUhpRSlGgVS01oFkdAt4U1EjPfK3V9lChoBmgJaA9DCPhvXpz4z2pAlIaUUpRoFU1cBWgWR0C3hTuu/1xsdX2UKGgGaAloD0MIsJKP3QUxaECUhpRSlGgVTRsGaBZHQLeGMX6InBt1fZQoaAZoCWgPQwgZqmIqfTlnQJSGlFKUaBVNQAZoFkdAt4Y52TxG2HV9lChoBmgJaA9DCCdPWU3Xo2lAlIaUUpRoFU29BWgWR0C3hl6yKNyYdX2UKGgGaAloD0MIweCaO3pDaECUhpRSlGgVTQIGaBZHQLeGeFwkxAV1fZQoaAZoCWgPQwi858ByBMxpQJSGlFKUaBVNoQVoFkdAt4aOoJiRXHV9lChoBmgJaA9DCEyKj09I6mhAlIaUUpRoFU3YBWgWR0C3hrJSzgMudX2UKGgGaAloD0MI7gVmhaIzaUCUhpRSlGgVTdwFaBZHQLeG2uZ1FH91fZQoaAZoCWgPQwjiytk7IxVpQJSGlFKUaBVN4QVoFkdAt4epxYJVsHV9lChoBmgJaA9DCNUHkncOJ2hAlIaUUpRoFU0oBmgWR0C3knm4iHIqdX2UKGgGaAloD0MIzo3pCUu2aECUhpRSlGgVTfcFaBZHQLeSf6IFeOZ1fZQoaAZoCWgPQwhYG2MnvABEQJSGlFKUaBVNJwRoFkdAt5K//FR51XV9lChoBmgJaA9DCNxGA3iLGmhAlIaUUpRoFU0aBmgWR0C3kzshxHXmdX2UKGgGaAloD0MIE9bG2IkGakCUhpRSlGgVTZMFaBZHQLeTnIYm9g51fZQoaAZoCWgPQwjl1M4wNbpnQJSGlFKUaBVNPwZoFkdAt5Onmhdt23V9lChoBmgJaA9DCKq3BrZKKWlAlIaUUpRoFU3QBWgWR0C3k8rXL/0edX2UKGgGaAloD0MIxFxStV3fZ0CUhpRSlGgVTS4GaBZHQLeUUKxs2vV1fZQoaAZoCWgPQwhFZi5weURpQJSGlFKUaBVNxwVoFkdAt5T7k4m1IHV9lChoBmgJaA9DCCBj7lrCQGlAlIaUUpRoFU3UBWgWR0C3lQ5YPoV3dX2UKGgGaAloD0MIyXa+n5roaUCUhpRSlGgVTZsFaBZHQLeVH2QXAM51fZQoaAZoCWgPQwhpO6buyvppQJSGlFKUaBVNkgVoFkdAt5VRpmEoOXV9lChoBmgJaA9DCGMIAI6902dAlIaUUpRoFU0oBmgWR0C3lXUxASnMdX2UKGgGaAloD0MITKd1G9ROaECUhpRSlGgVTRUGaBZHQLeVlbLlmvp1fZQoaAZoCWgPQwjk2eVbnxpoQJSGlFKUaBVNIgZoFkdAt5XquMdcS3V9lChoBmgJaA9DCBh9BWnGuGpAlIaUUpRoFU1jBWgWR0C3liSncclxdX2UKGgGaAloD0MIh4px/iYgaUCUhpRSlGgVTc8FaBZHQLehHNyYG+t1fZQoaAZoCWgPQwh1IOupVaFoQJSGlFKUaBVNAQZoFkdAt6FJvbXYlXV9lChoBmgJaA9DCFvs9lllnmlAlIaUUpRoFU2zBWgWR0C3oU3sC1Z1dX2UKGgGaAloD0MIWkbqPZX1aECUhpRSlGgVTe4FaBZHQLeh9yGi5/d1fZQoaAZoCWgPQwjBO/n02LJoQJSGlFKUaBVN+AVoFkdAt6JqXeFcp3V9lChoBmgJaA9DCJimCHD6N2hAlIaUUpRoFU0iBmgWR0C3ooDER8MNdX2UKGgGaAloD0MIrFPle8bLaECUhpRSlGgVTe0FaBZHQLeihUHY6GR1fZQoaAZoCWgPQwjwNJnxNqFoQJSGlFKUaBVN9gVoFkdAt6MSnZTQ3XV9lChoBmgJaA9DCLA8SE8R72hAlIaUUpRoFU3pBWgWR0C3o8ScLBsRdX2UKGgGaAloD0MIWJHRAUl0ZkCUhpRSlGgVTUAGaBZHQLej9w/PgNx1fZQoaAZoCWgPQwjQ04BBUvVlQJSGlFKUaBVNQAZoFkdAt6Qadat9yHV9lChoBmgJaA9DCIPg8e3dg2lAlIaUUpRoFU23BWgWR0C3pCUL2HtXdX2UKGgGaAloD0MIsktUb420Z0CUhpRSlGgVTT8GaBZHQLekTLuhK151fZQoaAZoCWgPQwizfF2G/8lnQJSGlFKUaBVNOAZoFkdAt6Rq1a4c3nV9lChoBmgJaA9DCN7jTBO2SmlAlIaUUpRoFU3MBWgWR0C3pMROclPadX2UKGgGaAloD0MIuqEpO/0TaECUhpRSlGgVTSQGaBZHQLek0NOuaF51fZQoaAZoCWgPQwgU61T5nu1pQJSGlFKUaBVNmgVoFkdAt6WB4X40uXV9lChoBmgJaA9DCIP7AQ8MnWlAlIaUUpRoFU28BWgWR0C3pczQRf4RdX2UKGgGaAloD0MIdqT6zq8EaECUhpRSlGgVTQ8GaBZHQLev/jgAIY51fZQoaAZoCWgPQwiZDTLJyBFPwJSGlFKUaBVNTgJoFkdAt7CGhg3Lm3V9lChoBmgJaA9DCIofY+7aqGhAlIaUUpRoFU33BWgWR0C3sJjqW1MNdX2UKGgGaAloD0MIilsFMdBfaUCUhpRSlGgVTcEFaBZHQLew/P6sQup1fZQoaAZoCWgPQwhJ9DKK5eVnQJSGlFKUaBVNLwZoFkdAt7E56By0bHV9lChoBmgJaA9DCEHV6NUAOWhAlIaUUpRoFU0wBmgWR0C3sVB0+1SgdX2UKGgGaAloD0MINBE2PL3baUCUhpRSlGgVTakFaBZHQLexeFX7tRh1fZQoaAZoCWgPQwgbE2IuqWI7QJSGlFKUaBVNbwRoFkdAt7HZ98Z1m3V9lChoBmgJaA9DCB3lYDYBlGhAlIaUUpRoFU0CBmgWR0C3snIOlO45dX2UKGgGaAloD0MIkBMmjObjaUCUhpRSlGgVTacFaBZHQLeygA6Mir11fZQoaAZoCWgPQwhod0gxQGhqQJSGlFKUaBVNfgVoFkdAt7KRyfcvd3V9lChoBmgJaA9DCFch5SdVhmhAlIaUUpRoFU0HBmgWR0C3sqlp9JBgdX2UKGgGaAloD0MIDamieBU7aUCUhpRSlGgVTdMFaBZHQLeyrfDUExJ1fZQoaAZoCWgPQwiGHFvPEFYpwJSGlFKUaBVNBANoFkdAt7LoSJ0nxHV9lChoBmgJaA9DCObmG9E9k2hAlIaUUpRoFU0FBmgWR0C3s4FGoaUBdX2UKGgGaAloD0MIwr0yb9WdZkCUhpRSlGgVTUAGaBZHQLe0YP8AJcB1fZQoaAZoCWgPQwi9VGzM62gyQJSGlFKUaBVNBgRoFkdAt7Rl4u9OAXV9lChoBmgJaA9DCM3OoncqvmhAlIaUUpRoFU3zBWgWR0C3tHBMFlkIdX2UKGgGaAloD0MIERrBxvWNaECUhpRSlGgVTfYFaBZHQLe0sGHYYix1fZQoaAZoCWgPQwg3ABsQoZNpQJSGlFKUaBVNtwVoFkdAt78KiSJTEXV9lChoBmgJaA9DCCXP9X04cWhAlIaUUpRoFU0IBmgWR0C3v60J8fFKdX2UKGgGaAloD0MICAWlaOWHaUCUhpRSlGgVTbYFaBZHQLe/v97F85V1fZQoaAZoCWgPQwj1DrdDwxlqQJSGlFKUaBVNkQVoFkdAt7/K+XZ5A3V9lChoBmgJaA9DCJROJJhqUmlAlIaUUpRoFU3TBWgWR0C3wF+XNTtLdX2UKGgGaAloD0MIG0rtRbRFTECUhpRSlGgVTX0FaBZHQLfA6pj+aSd1fZQoaAZoCWgPQwgFwePbu0xqQJSGlFKUaBVNhAVoFkdAt8D0kIHC43V9lChoBmgJaA9DCNTuVwE+zGhAlIaUUpRoFU36BWgWR0C3wTXFPznSdX2UKGgGaAloD0MIsRpLWJtjZkCUhpRSlGgVTUAGaBZHQLfBTki2Ujd1fZQoaAZoCWgPQwgKL8Gpj+NnQJSGlFKUaBVNOAZoFkdAt8FWHk92YHV9lChoBmgJaA9DCCB7vfvjuGdAlIaUUpRoFU04BmgWR0C3wb0VFhG6dX2UKGgGaAloD0MIWaMeolFcaUCUhpRSlGgVTcgFaBZHQLfB/YkmhM91fZQoaAZoCWgPQwiqDONukJtpQJSGlFKUaBVNtQVoFkdAt8Lbq8lHBnV9lChoBmgJaA9DCGlXIeWnr2hAlIaUUpRoFU33BWgWR0C3wwXCj1wpdX2UKGgGaAloD0MIlS2SdqMtUUCUhpRSlGgVTTgGaBZHQLfDNXbM5fd1fZQoaAZoCWgPQwgRNdHnI95oQJSGlFKUaBVN5wVoFkdAt8NEtCiRGXV9lChoBmgJaA9DCPtbAvBPTmpAlIaUUpRoFU1+BWgWR0C3w1vM8ox6dX2UKGgGaAloD0MI2Vw1zxHQaUCUhpRSlGgVTbEFaBZHQLfOJzJZGKB1fZQoaAZoCWgPQwgrMGR1q8tpQJSGlFKUaBVNqwVoFkdAt84tL9MsYnV9lChoBmgJaA9DCIlBYOVQL2hAlIaUUpRoFU0kBmgWR0C3zm7KifxudX2UKGgGaAloD0MIAYblz7csXsCUhpRSlGgVS0BoFkdAt86g7uDzy3V9lChoBmgJaA9DCJ3VAnvM92hAlIaUUpRoFU3fBWgWR0C3zvDb349HdX2UKGgGaAloD0MIpBthUZGNaUCUhpRSlGgVTcAFaBZHQLfPa/k/8l51fZQoaAZoCWgPQwhzLzArFA9qQJSGlFKUaBVNlAVoFkdAt8+jE5yU93V9lChoBmgJaA9DCNCaH3/pDmlAlIaUUpRoFU3dBWgWR0C3z8RL0z0pdX2UKGgGaAloD0MIlzrI68ELZ0CUhpRSlGgVTUAGaBZHQLfPx6AOJ+F1fZQoaAZoCWgPQwg4wMx3cGtpQJSGlFKUaBVNugVoFkdAt8/JDc/MXHV9lChoBmgJaA9DCIV80LNZeGlAlIaUUpRoFU2+BWgWR0C30HHiWE9MdX2UKGgGaAloD0MIU3qmlxhOaECUhpRSlGgVTREGaBZHQLfQcznA6+51fZQoaAZoCWgPQwgK2Xkbm1lOQJSGlFKUaBVN8gRoFkdAt9Cx0yP+43V9lChoBmgJaA9DCHo57L5j+mhAlIaUUpRoFU3gBWgWR0C30ZVxsEaEdX2UKGgGaAloD0MItd/aiZKWaECUhpRSlGgVTfYFaBZHQLfR5R8twrF1fZQoaAZoCWgPQwhUOIJUitdoQJSGlFKUaBVN7wVoFkdAt9H297F85XV9lChoBmgJaA9DCAwBwLFn4GVAlIaUUpRoFU1ABmgWR0C30hD1TR6XdX2UKGgGaAloD0MIAYqRJXNoXMCUhpRSlGgVS1xoFkdAt9It/z8P4HV9lChoBmgJaA9DCG/0MR8QqBFAlIaUUpRoFU1TA2gWR0C30mAAAAAAdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3910, "n_steps": 1600, "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, "system_info": {"OS": "Linux-6.0.12-zen1-1-zen-x86_64-with-glibc2.36 #1 ZEN SMP PREEMPT_DYNAMIC Thu, 08 Dec 2022 11:03:40 +0000", "Python": "3.10.8", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0", "GPU Enabled": "True", "Numpy": "1.23.4", "Gym": "0.21.0"}}
+{"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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f57120cf5b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f57120cf640>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f57120cf6d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f57120cf760>", "_build": "<function ActorCriticPolicy._build at 0x7f57120cf7f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f57120cf880>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f57120cf910>", "_predict": "<function ActorCriticPolicy._predict at 0x7f57120cf9a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f57120cfa30>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f57120cfac0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f57120cfb50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f57120c7b80>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [24], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "n_envs": 1, "num_timesteps": 10009600, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1671097329495755806, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_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": -0.0009600000000000719, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVfhAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIWOTXD7G5aUCUhpRSlIwBbJRNtgWMAXSUR0C3hPoa1kUcdX2UKGgGaAloD0MIK/aX3ZNEXsCUhpRSlGgVS01oFkdAt4U1EjPfK3V9lChoBmgJaA9DCPhvXpz4z2pAlIaUUpRoFU1cBWgWR0C3hTuu/1xsdX2UKGgGaAloD0MIsJKP3QUxaECUhpRSlGgVTRsGaBZHQLeGMX6InBt1fZQoaAZoCWgPQwgZqmIqfTlnQJSGlFKUaBVNQAZoFkdAt4Y52TxG2HV9lChoBmgJaA9DCCdPWU3Xo2lAlIaUUpRoFU29BWgWR0C3hl6yKNyYdX2UKGgGaAloD0MIweCaO3pDaECUhpRSlGgVTQIGaBZHQLeGeFwkxAV1fZQoaAZoCWgPQwi858ByBMxpQJSGlFKUaBVNoQVoFkdAt4aOoJiRXHV9lChoBmgJaA9DCEyKj09I6mhAlIaUUpRoFU3YBWgWR0C3hrJSzgMudX2UKGgGaAloD0MI7gVmhaIzaUCUhpRSlGgVTdwFaBZHQLeG2uZ1FH91fZQoaAZoCWgPQwjiytk7IxVpQJSGlFKUaBVN4QVoFkdAt4epxYJVsHV9lChoBmgJaA9DCNUHkncOJ2hAlIaUUpRoFU0oBmgWR0C3knm4iHIqdX2UKGgGaAloD0MIzo3pCUu2aECUhpRSlGgVTfcFaBZHQLeSf6IFeOZ1fZQoaAZoCWgPQwhYG2MnvABEQJSGlFKUaBVNJwRoFkdAt5K//FR51XV9lChoBmgJaA9DCNxGA3iLGmhAlIaUUpRoFU0aBmgWR0C3kzshxHXmdX2UKGgGaAloD0MIE9bG2IkGakCUhpRSlGgVTZMFaBZHQLeTnIYm9g51fZQoaAZoCWgPQwjl1M4wNbpnQJSGlFKUaBVNPwZoFkdAt5Onmhdt23V9lChoBmgJaA9DCKq3BrZKKWlAlIaUUpRoFU3QBWgWR0C3k8rXL/0edX2UKGgGaAloD0MIxFxStV3fZ0CUhpRSlGgVTS4GaBZHQLeUUKxs2vV1fZQoaAZoCWgPQwhFZi5weURpQJSGlFKUaBVNxwVoFkdAt5T7k4m1IHV9lChoBmgJaA9DCCBj7lrCQGlAlIaUUpRoFU3UBWgWR0C3lQ5YPoV3dX2UKGgGaAloD0MIyXa+n5roaUCUhpRSlGgVTZsFaBZHQLeVH2QXAM51fZQoaAZoCWgPQwhpO6buyvppQJSGlFKUaBVNkgVoFkdAt5VRpmEoOXV9lChoBmgJaA9DCGMIAI6902dAlIaUUpRoFU0oBmgWR0C3lXUxASnMdX2UKGgGaAloD0MITKd1G9ROaECUhpRSlGgVTRUGaBZHQLeVlbLlmvp1fZQoaAZoCWgPQwjk2eVbnxpoQJSGlFKUaBVNIgZoFkdAt5XquMdcS3V9lChoBmgJaA9DCBh9BWnGuGpAlIaUUpRoFU1jBWgWR0C3liSncclxdX2UKGgGaAloD0MIh4px/iYgaUCUhpRSlGgVTc8FaBZHQLehHNyYG+t1fZQoaAZoCWgPQwh1IOupVaFoQJSGlFKUaBVNAQZoFkdAt6FJvbXYlXV9lChoBmgJaA9DCFvs9lllnmlAlIaUUpRoFU2zBWgWR0C3oU3sC1Z1dX2UKGgGaAloD0MIWkbqPZX1aECUhpRSlGgVTe4FaBZHQLeh9yGi5/d1fZQoaAZoCWgPQwjBO/n02LJoQJSGlFKUaBVN+AVoFkdAt6JqXeFcp3V9lChoBmgJaA9DCJimCHD6N2hAlIaUUpRoFU0iBmgWR0C3ooDER8MNdX2UKGgGaAloD0MIrFPle8bLaECUhpRSlGgVTe0FaBZHQLeihUHY6GR1fZQoaAZoCWgPQwjwNJnxNqFoQJSGlFKUaBVN9gVoFkdAt6MSnZTQ3XV9lChoBmgJaA9DCLA8SE8R72hAlIaUUpRoFU3pBWgWR0C3o8ScLBsRdX2UKGgGaAloD0MIWJHRAUl0ZkCUhpRSlGgVTUAGaBZHQLej9w/PgNx1fZQoaAZoCWgPQwjQ04BBUvVlQJSGlFKUaBVNQAZoFkdAt6Qadat9yHV9lChoBmgJaA9DCIPg8e3dg2lAlIaUUpRoFU23BWgWR0C3pCUL2HtXdX2UKGgGaAloD0MIsktUb420Z0CUhpRSlGgVTT8GaBZHQLekTLuhK151fZQoaAZoCWgPQwizfF2G/8lnQJSGlFKUaBVNOAZoFkdAt6Rq1a4c3nV9lChoBmgJaA9DCN7jTBO2SmlAlIaUUpRoFU3MBWgWR0C3pMROclPadX2UKGgGaAloD0MIuqEpO/0TaECUhpRSlGgVTSQGaBZHQLek0NOuaF51fZQoaAZoCWgPQwgU61T5nu1pQJSGlFKUaBVNmgVoFkdAt6WB4X40uXV9lChoBmgJaA9DCIP7AQ8MnWlAlIaUUpRoFU28BWgWR0C3pczQRf4RdX2UKGgGaAloD0MIdqT6zq8EaECUhpRSlGgVTQ8GaBZHQLev/jgAIY51fZQoaAZoCWgPQwiZDTLJyBFPwJSGlFKUaBVNTgJoFkdAt7CGhg3Lm3V9lChoBmgJaA9DCIofY+7aqGhAlIaUUpRoFU33BWgWR0C3sJjqW1MNdX2UKGgGaAloD0MIilsFMdBfaUCUhpRSlGgVTcEFaBZHQLew/P6sQup1fZQoaAZoCWgPQwhJ9DKK5eVnQJSGlFKUaBVNLwZoFkdAt7E56By0bHV9lChoBmgJaA9DCEHV6NUAOWhAlIaUUpRoFU0wBmgWR0C3sVB0+1SgdX2UKGgGaAloD0MINBE2PL3baUCUhpRSlGgVTakFaBZHQLexeFX7tRh1fZQoaAZoCWgPQwgbE2IuqWI7QJSGlFKUaBVNbwRoFkdAt7HZ98Z1m3V9lChoBmgJaA9DCB3lYDYBlGhAlIaUUpRoFU0CBmgWR0C3snIOlO45dX2UKGgGaAloD0MIkBMmjObjaUCUhpRSlGgVTacFaBZHQLeygA6Mir11fZQoaAZoCWgPQwhod0gxQGhqQJSGlFKUaBVNfgVoFkdAt7KRyfcvd3V9lChoBmgJaA9DCFch5SdVhmhAlIaUUpRoFU0HBmgWR0C3sqlp9JBgdX2UKGgGaAloD0MIDamieBU7aUCUhpRSlGgVTdMFaBZHQLeyrfDUExJ1fZQoaAZoCWgPQwiGHFvPEFYpwJSGlFKUaBVNBANoFkdAt7LoSJ0nxHV9lChoBmgJaA9DCObmG9E9k2hAlIaUUpRoFU0FBmgWR0C3s4FGoaUBdX2UKGgGaAloD0MIwr0yb9WdZkCUhpRSlGgVTUAGaBZHQLe0YP8AJcB1fZQoaAZoCWgPQwi9VGzM62gyQJSGlFKUaBVNBgRoFkdAt7Rl4u9OAXV9lChoBmgJaA9DCM3OoncqvmhAlIaUUpRoFU3zBWgWR0C3tHBMFlkIdX2UKGgGaAloD0MIERrBxvWNaECUhpRSlGgVTfYFaBZHQLe0sGHYYix1fZQoaAZoCWgPQwg3ABsQoZNpQJSGlFKUaBVNtwVoFkdAt78KiSJTEXV9lChoBmgJaA9DCCXP9X04cWhAlIaUUpRoFU0IBmgWR0C3v60J8fFKdX2UKGgGaAloD0MICAWlaOWHaUCUhpRSlGgVTbYFaBZHQLe/v97F85V1fZQoaAZoCWgPQwj1DrdDwxlqQJSGlFKUaBVNkQVoFkdAt7/K+XZ5A3V9lChoBmgJaA9DCJROJJhqUmlAlIaUUpRoFU3TBWgWR0C3wF+XNTtLdX2UKGgGaAloD0MIG0rtRbRFTECUhpRSlGgVTX0FaBZHQLfA6pj+aSd1fZQoaAZoCWgPQwgFwePbu0xqQJSGlFKUaBVNhAVoFkdAt8D0kIHC43V9lChoBmgJaA9DCNTuVwE+zGhAlIaUUpRoFU36BWgWR0C3wTXFPznSdX2UKGgGaAloD0MIsRpLWJtjZkCUhpRSlGgVTUAGaBZHQLfBTki2Ujd1fZQoaAZoCWgPQwgKL8Gpj+NnQJSGlFKUaBVNOAZoFkdAt8FWHk92YHV9lChoBmgJaA9DCCB7vfvjuGdAlIaUUpRoFU04BmgWR0C3wb0VFhG6dX2UKGgGaAloD0MIWaMeolFcaUCUhpRSlGgVTcgFaBZHQLfB/YkmhM91fZQoaAZoCWgPQwiqDONukJtpQJSGlFKUaBVNtQVoFkdAt8Lbq8lHBnV9lChoBmgJaA9DCGlXIeWnr2hAlIaUUpRoFU33BWgWR0C3wwXCj1wpdX2UKGgGaAloD0MIlS2SdqMtUUCUhpRSlGgVTTgGaBZHQLfDNXbM5fd1fZQoaAZoCWgPQwgRNdHnI95oQJSGlFKUaBVN5wVoFkdAt8NEtCiRGXV9lChoBmgJaA9DCPtbAvBPTmpAlIaUUpRoFU1+BWgWR0C3w1vM8ox6dX2UKGgGaAloD0MI2Vw1zxHQaUCUhpRSlGgVTbEFaBZHQLfOJzJZGKB1fZQoaAZoCWgPQwgrMGR1q8tpQJSGlFKUaBVNqwVoFkdAt84tL9MsYnV9lChoBmgJaA9DCIlBYOVQL2hAlIaUUpRoFU0kBmgWR0C3zm7KifxudX2UKGgGaAloD0MIAYblz7csXsCUhpRSlGgVS0BoFkdAt86g7uDzy3V9lChoBmgJaA9DCJ3VAnvM92hAlIaUUpRoFU3fBWgWR0C3zvDb349HdX2UKGgGaAloD0MIpBthUZGNaUCUhpRSlGgVTcAFaBZHQLfPa/k/8l51fZQoaAZoCWgPQwhzLzArFA9qQJSGlFKUaBVNlAVoFkdAt8+jE5yU93V9lChoBmgJaA9DCNCaH3/pDmlAlIaUUpRoFU3dBWgWR0C3z8RL0z0pdX2UKGgGaAloD0MIlzrI68ELZ0CUhpRSlGgVTUAGaBZHQLfPx6AOJ+F1fZQoaAZoCWgPQwg4wMx3cGtpQJSGlFKUaBVNugVoFkdAt8/JDc/MXHV9lChoBmgJaA9DCIV80LNZeGlAlIaUUpRoFU2+BWgWR0C30HHiWE9MdX2UKGgGaAloD0MIU3qmlxhOaECUhpRSlGgVTREGaBZHQLfQcznA6+51fZQoaAZoCWgPQwgK2Xkbm1lOQJSGlFKUaBVN8gRoFkdAt9Cx0yP+43V9lChoBmgJaA9DCHo57L5j+mhAlIaUUpRoFU3gBWgWR0C30ZVxsEaEdX2UKGgGaAloD0MItd/aiZKWaECUhpRSlGgVTfYFaBZHQLfR5R8twrF1fZQoaAZoCWgPQwhUOIJUitdoQJSGlFKUaBVN7wVoFkdAt9H297F85XV9lChoBmgJaA9DCAwBwLFn4GVAlIaUUpRoFU1ABmgWR0C30hD1TR6XdX2UKGgGaAloD0MIAYqRJXNoXMCUhpRSlGgVS1xoFkdAt9It/z8P4HV9lChoBmgJaA9DCG/0MR8QqBFAlIaUUpRoFU1TA2gWR0C30mAAAAAAdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 3910, "n_steps": 1600, "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, "system_info": {"OS": "Linux-6.0.12-zen1-1-zen-x86_64-with-glibc2.36 #1 ZEN SMP PREEMPT_DYNAMIC Thu, 08 Dec 2022 11:03:40 +0000", "Python": "3.10.8", "Stable-Baselines3": "1.6.2", "PyTorch": "1.13.0", "GPU Enabled": "True", "Numpy": "1.23.4", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 229.21047812668112, "std_reward": 63.56924403610953, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-16T01:34:59.976281"}
+{"mean_reward": 209.63066780234195, "std_reward": 82.30083863962741, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-16T01:38:51.012937"}