The aim of this code is solving a randomly generated square maze (dimension n) using a Q-Learning algorithm involving an epsilon-greedy policy.
A report has been done so as to help the user to better understand the code and the theory behind Q-Learning.
The user can choose the starting and ending points of the maze and its dimension n.
引用格式
Jonathan Sanz Carcelén (2024). SQUARE MAZE SOLVED USING Q-LEARNING & EPSILON-GREEDY POLICY (https://www.mathworks.com/matlabcentral/fileexchange/80146-square-maze-solved-using-q-learning-epsilon-greedy-policy), MATLAB Central File Exchange. 检索来源 .
MATLAB 版本兼容性
创建方式
R2020a
兼容任何版本
平台兼容性
Windows macOS Linux标签
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!