Deep Reinforcement Learning in Match-3 Game
Ildar Kamaldinov, Ilya Makarov · 2019 IEEE Conference on Games (CoG) · 2019
An increasing number of algorithms in deep reinforcement learning area creates new challenges for environments, particularly, for their comprehensive analysis and searching application areas. The key purpose of this article is to provide an extensible environment for researches. We consider a Match-3 game, which has simple gameplay, but challenging game design for engaging players. The article provides metrics for evaluation of agents and corresponding baselines in different scenarios.