In this project, I use Q learning, value and policy iteration to solve 5 * 5 and 25 * 25 maze puzzle.
The green square is start point and red squares are enf points.
In this project, I use Q learning, value and policy iteration to solve 5*5 and 25*25 maze puzzle
In this project, I use Q learning, value and policy iteration to solve 5 * 5 and 25 * 25 maze puzzle.
The green square is start point and red squares are enf points.
In this project, I use Q learning, value and policy iteration to solve 5*5 and 25*25 maze puzzle
MIT License