from easydict import EasyDict

# options={'PongNoFrameskip-v4', 'QbertNoFrameskip-v4', 'MsPacmanNoFrameskip-v4', 'SpaceInvadersNoFrameskip-v4', 'BreakoutNoFrameskip-v4', ...}
env_name = 'PongNoFrameskip-v4'

if env_name == 'PongNoFrameskip-v4':
    action_space_size = 6
elif env_name == 'QbertNoFrameskip-v4':
    action_space_size = 6
elif env_name == 'MsPacmanNoFrameskip-v4':
    action_space_size = 9
elif env_name == 'SpaceInvadersNoFrameskip-v4':
    action_space_size = 6
elif env_name == 'BreakoutNoFrameskip-v4':
    action_space_size = 4

# ==============================================================
# begin of the most frequently changed config specified by the user
# ==============================================================
# collector_env_num = 8
# n_episode = 8
# evaluator_env_num = 3
# num_simulations = 50
# update_per_collect = 1000
# batch_size = 256
# max_env_step = int(1e6)
# reanalyze_ratio = 0.
# chance_space_size = 4

# debug config
collector_env_num = 1
n_episode = 1
evaluator_env_num = 1
num_simulations = 5
update_per_collect = 10
batch_size = 2
max_env_step = int(1e6)
reanalyze_ratio = 0.
chance_space_size = 4
# ==============================================================
# end of the most frequently changed config specified by the user
# ==============================================================

atari_stochastic_muzero_config = dict(
    exp_name=
    f'data_stochastic_mz_ctree/{env_name[:-14]}_stochastic_muzero_ns{num_simulations}_upc{update_per_collect}_rr{reanalyze_ratio}_chance{chance_space_size}_seed0',
    env=dict(
        stop_value=int(1e6),
        env_name=env_name,
        obs_shape=(4, 96, 96),
        collector_env_num=collector_env_num,
        evaluator_env_num=evaluator_env_num,
        n_evaluator_episode=evaluator_env_num,
        manager=dict(shared_memory=False, ),
    ),
    policy=dict(
        model=dict(
            observation_shape=(4, 96, 96),
            frame_stack_num=4,
            action_space_size=action_space_size,
            chance_space_size=chance_space_size,
            downsample=True,
            self_supervised_learning_loss=True,  # default is False
            discrete_action_encoding_type='one_hot',
            norm_type='BN', 
        ),
        cuda=True,
        gumbel_algo=False,
        mcts_ctree=True,
        env_type='not_board_games',
        game_segment_length=400,
        use_augmentation=True,
        update_per_collect=update_per_collect,
        batch_size=batch_size,
        optim_type='Adam',
        lr_piecewise_constant_decay=False,
        learning_rate=3e-3,
        num_simulations=num_simulations,
        reanalyze_ratio=reanalyze_ratio,
        ssl_loss_weight=2,  # default is 0
        n_episode=n_episode,
        eval_freq=int(2e3),
        replay_buffer_size=int(1e6),  # the size/capacity of replay_buffer, in the terms of transitions.
        collector_env_num=collector_env_num,
        evaluator_env_num=evaluator_env_num,
    ),
)
atari_stochastic_muzero_config = EasyDict(atari_stochastic_muzero_config)
main_config = atari_stochastic_muzero_config

atari_stochastic_muzero_create_config = dict(
    env=dict(
        type='atari_lightzero',
        import_names=['zoo.atari.envs.atari_lightzero_env'],
    ),
    env_manager=dict(type='subprocess'),
    policy=dict(
        type='stochastic_muzero',
        import_names=['lzero.policy.stochastic_muzero'],
    ),
)
atari_stochastic_muzero_create_config = EasyDict(atari_stochastic_muzero_create_config)
create_config = atari_stochastic_muzero_create_config

if __name__ == "__main__":
    from lzero.entry import train_muzero
    train_muzero([main_config, create_config], seed=0, max_env_step=max_env_step)