RL之Q Learning：利用强化学习之Q Learning实现走迷宫—训练智能体走到迷宫(复杂迷宫)的宝藏位置

RL之Q Learning：利用强化学习之Q Learning实现走迷宫—训练智能体走到迷宫(复杂迷宫)的宝藏位置

目录

输出结果

设计思路

实现代码

测试记录全过程

输出结果

设计思路

实现代码

  

   

    

     

    
    

     

      from __future__ import print_function
     
    
   

    

     

    
    

     

      import numpy as np
     
    
   

    

     

    
    

     

      import time
     
    
   

    

     

    
    

     

      from env import Env
     
    
   

    

     

    
    

     

      from reprint import output
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      EPSILON = 0.1
     
    
   

    

     

    
    

     

      ALPHA = 0.1
     
    
   

    

     

    
    

     

      GAMMA = 0.9
     
    
   

    

     

    
    

     

      MAX_STEP = 30
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      np.random.seed(0)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      def epsilon_greedy(Q, state):
     
    
   

    

     

    
    

     
 if (np.random.uniform() > 1 - EPSILON) or ((Q[state, :] == 0).all()):
     
    
   

    

     

    
    

     

       action = np.random.randint(0, 4)  # 0~3
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       action = Q[state, :].argmax()
     
    
   

    

     

    
    

     
 return action
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      e = Env()
     
    
   

    

     

    
    

     

      Q = np.zeros((e.state_num, 4))
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      with output(output_type="list", initial_len=len(e.map), interval=0) as output_list:
     
    
   

    

     

    
    

     
 for i in range(100):
     
    
   

    

     

    
    

     

       e = Env()
     
    
   

    

     

    
    

     
 while (e.is_end is False) and (e.step < MAX_STEP):
     
    
   

    

     

    
    

     

       action = epsilon_greedy(Q, e.present_state)
     
    
   

    

     

    
    

     

       state = e.present_state
     
    
   

    

     

    
    

     

       reward = e.interact(action)
     
    
   

    

     

    
    

     

       new_state = e.present_state
     
    
   

    

     

    
    

     

       Q[state, action] = (1 - ALPHA) * Q[state, action] + \
     
    
   

    

     

    
    

     

       ALPHA * (reward + GAMMA * Q[new_state, :].max())
     
    
   

    

     

    
    

     

       e.print_map_with_reprint(output_list)
     
    
   

    

     

    
    

     

       time.sleep(0.1)
     
    
   

    

     

    
    

     
 for line_num in range(len(e.map)):
     
    
   

    

     

    
    

     
 if line_num == 0:
     
    
   

    

     

    
    

     

       output_list[0] = 'Episode:{} Total Step:{}, Total Reward:{}'.format(i, e.step, e.total_reward)
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       output_list[line_num] = ''
     
    
   

    

     

    
    

     

       time.sleep(2)
     
    
  
 

测试记录全过程

  

   

    

     

    
    

     

      开始
     
    
   

    

     

    
    

     

      ......... ......... .  x . ......... .  x . .A  x o . ......... .  x . .A  x o . . . ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .A  x o . .A . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .   x o . .A . ......... ......... .  x . .A  x o . .A . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . .A  x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x A . . A . ......... ......... .  x . .   x A . . . ......... ......... .  x . .   x A . . . ......... Episode:0 Total Step:17, Total Reward:100 .  x . .   x A . . . ......... Episode:0 Total Step:17, Total Reward:100 .   x A . . . ......... Episode:0 Total Step:17, Total Reward:100 . . ......... Episode:0 Total Step:17, Total Reward:100 ......... Episode:0 Total Step:17, Total Reward:100 ......... ......... .  x . ......... .  x . .A  x o . ......... .  x . .A  x o . . . ......... .  x . .A  x o . . . ......... 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ……
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ......... .   A   . .   x o . . . ......... Episode:2 Total Step:30, Total Reward:-5 .   A   . .   x o . . . ......... Episode:2 Total Step:30, Total Reward:-5 .   x o . . . ......... Episode:2 Total Step:30, Total Reward:-5 . . ......... Episode:2 Total Step:30, Total Reward:-5 ......... Episode:2 Total Step:30, Total Reward:-5 [F
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ……
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   xAo . . A  . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   x A . . . ......... ......... .  x . .   x A . . . ......... ......... .  x . .   x A . . . ......... Episode:98 Total Step:8, Total Reward:100 .  x . .   x A . . . ......... Episode:98 Total Step:8, Total Reward:100 .   x A . . . ......... Episode:98 Total Step:8, Total Reward:100 . . ......... Episode:98 Total Step:8, Total Reward:100 ......... Episode:98 Total Step:8, Total Reward:100 ......... ......... . Ax . ......... . Ax . .   x o . ......... . Ax . .   x o . . . ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... . Ax . .   x o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . . A x o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . . A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .  Ax o . .  A . ......... ......... .  x . .  Ax o . . . ......... ......... .  x . .  Ax o . . . ......... ......... .  x . .  Ax o . . . ......... ......... .  x . .  Ax o . . . ......... ......... .  x . .   x o . . . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .  A . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . .   A   . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   x o . . A  . ......... ......... .  x . .   xAo . . A  . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   xAo . . . ......... ......... .  x . .   x A . . . ......... ......... .  x . .   x A . . . ......... ......... .  x . .   x A . . . ......... Episode:99 Total Step:11, Total Reward:100 .  x . .   x A . . . ......... Episode:99 Total Step:11, Total Reward:100 .   x A . . . ......... Episode:99 Total Step:11, Total Reward:100 . . ......... Episode:99 Total Step:11, Total Reward:100 ......... Episode:99 Total Step:11, Total Reward:100 Episode:99 Total Step:11, Total Reward:100 
     
    
   

    

     

    
    

     
 
     
    
  
 

文章来源: yunyaniu.blog.csdn.net，作者：一个处女座的程序猿，版权归原作者所有，如需转载，请联系作者。

原文链接：yunyaniu.blog.csdn.net/article/details/83245633