{
    "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 0x7fac046f3ee0>",
        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fac046f3f70>",
        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fac046f7040>",
        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fac046f70d0>",
        "_build": "<function ActorCriticPolicy._build at 0x7fac046f7160>",
        "forward": "<function ActorCriticPolicy.forward at 0x7fac046f71f0>",
        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fac046f7280>",
        "_predict": "<function ActorCriticPolicy._predict at 0x7fac046f7310>",
        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fac046f73a0>",
        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fac046f7430>",
        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fac046f74c0>",
        "__abstractmethods__": "frozenset()",
        "_abc_impl": "<_abc_data object at 0x7fac046ee900>"
    },
    "verbose": 1,
    "policy_kwargs": {},
    "observation_space": {
        ":type:": "<class 'gym.spaces.box.Box'>",
        ":serialized:": "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",
        "dtype": "float32",
        "_shape": [
            8
        ],
        "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
        "high": "[inf inf inf inf inf inf inf inf]",
        "bounded_below": "[False False False False False False False False]",
        "bounded_above": "[False False False False False False False False]",
        "_np_random": null
    },
    "action_space": {
        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
        "n": 4,
        "_shape": [],
        "dtype": "int64",
        "_np_random": null
    },
    "n_envs": 256,
    "num_timesteps": 20185088,
    "_total_timesteps": 20000000,
    "_num_timesteps_at_start": 0,
    "seed": null,
    "action_noise": null,
    "start_time": 1652917474.5945807,
    "learning_rate": 0.0003,
    "tensorboard_log": null,
    "lr_schedule": {
        ":type:": "<class 'function'>",
        ":serialized:": "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"
    },
    "_last_obs": {
        ":type:": "<class 'numpy.ndarray'>",
        ":serialized:": "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"
    },
    "_last_episode_starts": {
        ":type:": "<class 'numpy.ndarray'>",
        ":serialized:": "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"
    },
    "_last_original_obs": null,
    "_episode_num": 0,
    "use_sde": false,
    "sde_sample_freq": -1,
    "_current_progress_remaining": -0.009254400000000107,
    "ep_info_buffer": {
        ":type:": "<class 'collections.deque'>",
        ":serialized:": "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"
    },
    "ep_success_buffer": {
        ":type:": "<class 'collections.deque'>",
        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
    },
    "_n_updates": 308,
    "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
}