Book
Open access
Jul 2026
Evolving Maze Environments for Deep Q-Learning via Evolutionary Algorithms
A Maze Evolution framework, denoted as ME, is proposed, where an evolutionary algorithm searches a constrained space of grid-based mazes to produce a best evolved environment set for RL with desirable properties (e.g., feasibility and controlled structural difficulty).
Yan-Shun Huang, P. Harn
· GECCO Companion · 0 citations