{
    "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 0x78105b6b5a20>",
        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78105b6b5ab0>",
        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78105b6b5b40>",
        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78105b6b5bd0>",
        "_build": "<function ActorCriticPolicy._build at 0x78105b6b5c60>",
        "forward": "<function ActorCriticPolicy.forward at 0x78105b6b5cf0>",
        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78105b6b5d80>",
        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78105b6b5e10>",
        "_predict": "<function ActorCriticPolicy._predict at 0x78105b6b5ea0>",
        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78105b6b5f30>",
        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78105b6b5fc0>",
        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78105b6b6050>",
        "__abstractmethods__": "frozenset()",
        "_abc_impl": "<_abc._abc_data object at 0x78105c0bc180>"
    },
    "verbose": 1,
    "policy_kwargs": {},
    "num_timesteps": 1024000,
    "_total_timesteps": 1000000,
    "_num_timesteps_at_start": 0,
    "seed": null,
    "action_noise": null,
    "start_time": 1729680681149217421,
    "learning_rate": 0.0003,
    "tensorboard_log": null,
    "_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": -0.02400000000000002,
    "_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": 4,
    "observation_space": {
        ":type:": "<class 'gymnasium.spaces.box.Box'>",
        ":serialized:": "gAWVFgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgRKJYEAAAAAAAAAAEBAQGUaBVLBIWUaBl0lFKUjAZfc2hhcGWUSwSFlIwDbG93lGgRKJYQAAAAAAAAAJqZmcD//3//UHfWvv//f/+UaAtLBIWUaBl0lFKUjARoaWdolGgRKJYQAAAAAAAAAJqZmUD//39/UHfWPv//f3+UaAtLBIWUaBl0lFKUjAhsb3dfcmVwcpSMPVstNC44MDAwMDAyZSswMCAtMy40MDI4MjM1ZSszOCAtNC4xODg3OTAzZS0wMSAtMy40MDI4MjM1ZSszOF2UjAloaWdoX3JlcHKUjDlbNC44MDAwMDAyZSswMCAzLjQwMjgyMzVlKzM4IDQuMTg4NzkwM2UtMDEgMy40MDI4MjM1ZSszOF2UjApfbnBfcmFuZG9tlE51Yi4=",
        "dtype": "float32",
        "bounded_below": "[ True  True  True  True]",
        "bounded_above": "[ True  True  True  True]",
        "_shape": [
            4
        ],
        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
        "_np_random": null
    },
    "action_space": {
        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
        "n": "2",
        "start": "0",
        "_shape": [],
        "dtype": "int64",
        "_np_random": null
    },
    "n_envs": 1000,
    "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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"
    }
}