介绍
样例来自A Painless Q-learning Tutorial (一个 Q-learning 算法的简明教程)
简单来说就是从某个房间开始,找到去目标房间的路径。
代码实现
import numpy as np
from tqdm import tqdm, trange
room_num = 6
room_paths = [(0, 4), (3, 4), (3, 1), (1, 5), (2, 3), (4, 5)]
target_room = 5
# Q 矩阵,默认值填充0
Q = np.zeros((room_num, room_num))
# R 矩阵,默认值填充-1
reward