{ "policy_class": { ":type:": "", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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__": "", "_get_constructor_parameters": "", "reset_noise": "", "_build_mlp_extractor": "", "_build": "", "forward": "", "_get_action_dist_from_latent": "", "_predict": "", "evaluate_actions": "", "get_distribution": "", "predict_values": "", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f7e91da2de0>" }, "verbose": 1, "policy_kwargs": { ":type:": "", ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "", "optimizer_kwargs": { "alpha": 0.99, "eps": 1e-05, "weight_decay": 0 } }, "observation_space": { ":type:": "", ":serialized:": "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", "dtype": "float32", "_shape": [ 28 ], "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 -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 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\n 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\n False False False False]", "_np_random": null }, "action_space": { ":type:": "", ":serialized:": "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", "dtype": "float32", "_shape": [ 8 ], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True True True True True True True True]", "bounded_above": "[ True True True True True True True True]", "_np_random": null }, "n_envs": 4, "num_timesteps": 5024, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1668008238714695777, "learning_rate": 0.00096, "tensorboard_log": "./tensorboard", "lr_schedule": { ":type:": "", ":serialized:": "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" }, "_last_obs": { ":type:": "", ":serialized:": "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" }, "_last_episode_starts": { ":type:": "", ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg==" }, "_last_original_obs": { ":type:": "", ":serialized:": "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" }, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": -0.0047999999999999154, "ep_info_buffer": { ":type:": "", ":serialized:": "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" }, "ep_success_buffer": { ":type:": "", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg==" }, "_n_updates": 157, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false }