The goal of this project is to use deep reinforcement learning approaches to solve a simple 2D maze. The basis of the code is taken from https://samyzaf.com/ML/rl/qmaze.html.
n_epoch: 390, max_mem: 1000, data: 50, time: 6.90 minutes
isaiahchen28/MazeSolver
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|