使用matlab在机器人走迷宫环境中测试Q-learninng和Sarsa
这个环境以往都是作为动态规划的场景,在这个任务里,我使用Q-learning和Sarsa分别编写matlab代码进行测试
其中15,16为左上角以及右下角位置,设置为终点,给与+1奖励。
参数
alpha = 0.05;
gamma = 1;
len = 1000;总步数,值越大时间越长,稳定性收敛性越好,可以继续增大以获得更好的效果。
训练时,随机给定初始状态,训练agnet。测试时同样随机给点,结果证明其都可以快速到达与之最近的终点。
最终得到的Q_Learning的Q表和Sarsa的Q表如下:
-
Notifications
You must be signed in to change notification settings - Fork 0
wangjunhe8127/Q_learning-and-Saras-using-Matlab
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
使用matlab在机器人走迷宫环境中测试Q-learninng和Sarsa
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published