Reinforcement Learning (original) (raw)

`import numpy as np import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap

maze = np.array([ [0, 1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 1], [1, 1, 1, 0, 1, 0, 1, 1, 0, 1], [1, 0, 0, 0, 0, 0, 1, 0, 0, 1], [1, 0, 1, 1, 1, 1, 1, 0, 1, 1], [1, 0, 1, 0, 0, 0, 0, 0, 1, 1], [1, 0, 1, 0, 1, 1, 1, 0, 1, 1], [1, 0, 1, 0, 1, 0, 0, 0, 1, 1], [1, 0, 1, 0, 1, 0, 1, 0, 0, 1], [1, 1, 1, 0, 1, 1, 1, 1, 0, 0] ])

start = (0, 0) goal = (9, 9)

`