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

RL之SARSA：利用强化学习之SARSA实现走迷宫—训练智能体走到迷宫(复杂陷阱迷宫)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

后期更新……

 

 

 

 

测试记录全过程

……
                                                                     .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:11 Total Step:44, Total Reward:100                                                                              .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:11 Total Step:44, Total Reward:100                                                                              .     A .                                                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:11 Total Step:44, Total Reward:100                                                                              .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:11 Total Step:44, Total Reward:100                                                                              .........                                                                                                                                                                                                                                       Episode:11 Total Step:44, Total Reward:100                                                                                                                                                                                                      .........                                                                                                               .........                                                                                                               . A     .                                                                                                               .........                                                                                                               . A     .                                                                                                               .     o .                                                                                                               .........                                                                                                               . A     .                                                                                                               .     o .                                                                                                               .       .                                                                                                               .........                                                                                                               . A     .                                                                                                               .     o .                                                                                                               .       .                                                                                                               .........                                                                                                               

……
                                                       .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:31 Total Step:6, Total Reward:100                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:31 Total Step:6, Total Reward:100                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:31 Total Step:6, Total Reward:100                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:31 Total Step:6, Total Reward:100                                                                               .........                                                                                                                                                                                                                                       Episode:31 Total Step:6, Total Reward:100                                                                                                                                                                                                       .........                                                                                                               .........                                                                                                               .       .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .       .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .       .                                                                                                               .........                                                                                                                                                                                              .........                                                                                                               Episode:42 Total Step:6, Total Reward:100                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:42 Total Step:6, Total Reward:100                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:42 Total Step:6, Total Reward:100                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:42 Total Step:6, Total Reward:100                                                                               .........                                                                                                                                                                                                                                       Episode:42 Total Step:6, Total Reward:100                                                                                                                                                                                                       .........                                                                                                               .........                                                                                                               .       .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .       .                                                                                                               .........                                                                                                               .       .                                                                                                               .A    o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........  


……

.........                                                                                                               .       .                                                                                                               . A   o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .  A  o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .  A  o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .  A  o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .  A  o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .  A  o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .   A o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .   A o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .   A o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .   A o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .   A o .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .    Ao .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               .........                                                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:99 Total Step:8, Total Reward:100                                                                               .       .                                                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                               Episode:99 Total Step:8, Total Reward:100                                                                               .     A .                                                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:99 Total Step:8, Total Reward:100                                                                               .       .                                                                                                               .........                                                                                                                                                                                                                                       Episode:99 Total Step:8, Total Reward:100                                                                               .........                                                                                                                                                                                                                                       Episode:99 Total Step:8, Total Reward:100                                                                                                                                                                                                       Episode:99 Total Step:8, Total Reward:100