File size: 3,348 Bytes
079c32c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
from easydict import EasyDict
# ==============================================================
# begin of the most frequently changed config specified by the user
# ==============================================================
env_name = 'game_2048'
action_space_size = 4
collector_env_num = 8
n_episode = 8
evaluator_env_num = 3
num_simulations = 100
update_per_collect = 200
batch_size = 512
max_env_step = int(5e6)
reanalyze_ratio = 0.
num_of_possible_chance_tile = 2
chance_space_size = 16 * num_of_possible_chance_tile
# ==============================================================
# end of the most frequently changed config specified by the user
# ==============================================================
atari_muzero_config = dict(
exp_name=f'data_mz_ctree/game_2048_npct-{num_of_possible_chance_tile}_muzero_ns{num_simulations}_upc{update_per_collect}_rr{reanalyze_ratio}_bs{batch_size}_sslw2_seed0',
env=dict(
stop_value=int(1e6),
env_name=env_name,
obs_shape=(16, 4, 4),
obs_type='dict_encoded_board',
raw_reward_type='raw', # 'merged_tiles_plus_log_max_tile_num'
reward_normalize=False,
reward_norm_scale=100,
max_tile=int(2 ** 16), # 2**11=2048, 2**16=65536
num_of_possible_chance_tile=num_of_possible_chance_tile,
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=(16, 4, 4),
action_space_size=action_space_size,
image_channel=16,
# NOTE: whether to use the self_supervised_learning_loss. default is False
self_supervised_learning_loss=True,
),
mcts_ctree=True,
gumbel_algo=False,
cuda=True,
game_segment_length=200,
update_per_collect=update_per_collect,
batch_size=batch_size,
td_steps=10,
discount_factor=0.999,
manual_temperature_decay=True,
threshold_training_steps_for_final_temperature=int(1e5),
optim_type='Adam',
lr_piecewise_constant_decay=False,
learning_rate=3e-3,
# (float) Weight decay for training policy network.
weight_decay=1e-4,
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_muzero_config = EasyDict(atari_muzero_config)
main_config = atari_muzero_config
atari_muzero_create_config = dict(
env=dict(
type='game_2048',
import_names=['zoo.game_2048.envs.game_2048_env'],
),
env_manager=dict(type='subprocess'),
policy=dict(
type='muzero',
import_names=['lzero.policy.muzero'],
),
)
atari_muzero_create_config = EasyDict(atari_muzero_create_config)
create_config = atari_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)
|