RL
飞翔的貅貅
这个作者很懒,什么都没留下…
展开
-
RL-mofan
import numpy as np import pandas as pd import time N_STATES = 6 ACTIONS = ['left', 'right'] def build_q_table(n_states, actions): table = pd.DataFrame(np.zeros((n_states, len(actions))),columns...原创 2019-10-18 11:49:52 · 157 阅读 · 0 评论 -
强化学习圣经-GridWorld实现
import numpy as np import matplotlib.pyplot as plt grid_size = 5 posA = [0,1] primeA = [4,1] posB = [0,3] primeB = [2,3] discount = 0.9 actions = ['L', 'U', 'R', 'D'] actionProb = [[dict({'L':0.25, ...原创 2019-10-07 16:27:45 · 2517 阅读 · 0 评论