解决问题：从任何位置到6

视频课程地址：

强化学习算法系列教程及代码实现-Q-Learning_哔哩哔哩_bilibili

相应代码：

import numpy as np
import random

q = np.zeros((7, 7))
q = np.matrix(q)

r = np.array([[-1, -1, -1, 0, -1, -1, -1],
              [-1, -1, 0, -1, -1, -1, -1],
              [-1, 0, -1, 0, -1, 0, -1],
              [0, -1, 0, -1, 0, -1, -1],
              [-1, -1, -1, 0, -1, 0, 100],
              [-1, -1, 0, -1, 0, -1, 100],
              [-1, -1, -1, -1, 0, 0, 100]])
r = np.matrix(r)

gamma = 0.8
for i in range(1000):
    state = random.randint(0, 6)
    while state != 6:
        r_pos_action = []
        for action in range(7):
            if r[state, action] >= 0:
                r_pos_action.append(action)
        next_state = r_pos_action[random.randint(0, len(r_pos_action) - 1)]
        q[state, next_state] = r[state, next_state] + gamma * q[next_state].max()
        state = next_state


print(q)

state = random.randint(0, 6)
print("机器人处于{}".format(state))
count = 0
while state != 6:
    if count > 20:
        print("fail")
        break
    q_max = q[state].max()

    q_max_action = []
    for action in range(7):
        if q[state, action] == q_max:
            q_max_action.append(action)
    next_state = q_max_action[random.randint(0, len(q_max_action) - 1)]
    print('机器人 goes to {} 。'.format(next_state))
    state = next_state
    count += 1