exp_config = {
    'env': {
        'manager': {
            'episode_num': float("inf"),
            'max_retry': 1,
            'retry_type': 'reset',
            'auto_reset': True,
            'step_timeout': None,
            'reset_timeout': None,
            'retry_waiting_time': 0.1,
            'cfg_type': 'BaseEnvManagerDict'
        },
        'stop_value': -250,
        'collector_env_num': 10,
        'evaluator_env_num': 8,
        'act_scale': True,
        'n_evaluator_episode': 8
    },
    'policy': {
        'model': {
            'twin_critic': True,
            'action_space': 'reparameterization',
            'obs_shape': 3,
            'action_shape': 1,
            'actor_head_hidden_size': 128,
            'critic_head_hidden_size': 128
        },
        'learn': {
            'learner': {
                'train_iterations': 1000000000,
                'dataloader': {
                    'num_workers': 0
                },
                'log_policy': True,
                'hook': {
                    'load_ckpt_before_run': '',
                    'log_show_after_iter': 100,
                    'save_ckpt_after_iter': 10000,
                    'save_ckpt_after_run': True
                },
                'cfg_type': 'BaseLearnerDict'
            },
            'update_per_collect': 1,
            'batch_size': 128,
            'learning_rate_q': 0.001,
            'learning_rate_policy': 0.001,
            'learning_rate_alpha': 0.0003,
            'target_theta': 0.005,
            'discount_factor': 0.99,
            'alpha': 0.2,
            'auto_alpha': True,
            'log_space': True,
            'target_entropy': None,
            'ignore_done': True,
            'init_w': 0.003
        },
        'collect': {
            'collector': {},
            'n_sample': 10,
            'unroll_len': 1,
            'collector_logit': False
        },
        'eval': {
            'evaluator': {
                'eval_freq': 100,
                'render': {
                    'render_freq': -1,
                    'mode': 'train_iter'
                },
                'cfg_type': 'InteractionSerialEvaluatorDict',
                'n_episode': 8,
                'stop_value': -250
            }
        },
        'other': {
            'replay_buffer': {
                'replay_buffer_size': 100000
            }
        },
        'on_policy': False,
        'cuda': False,
        'multi_gpu': False,
        'bp_update_sync': True,
        'traj_len_inf': False,
        'type': 'sac',
        'priority': False,
        'priority_IS_weight': False,
        'random_collect_size': 1000,
        'transition_with_policy_data': True,
        'multi_agent': False,
        'cfg_type': 'SACPolicyDict'
    },
    'exp_name': 'Pendulum-v1-SAC',
    'seed': 0,
    'wandb_logger': {
        'gradient_logger': True,
        'video_logger': True,
        'plot_logger': True,
        'action_logger': True,
        'return_logger': False
    }
}