Abstract:
An increasing number of algorithms in deep reinforcement learning area creates new challenges for environments, particularly, for their comprehensive analysis and searchi...Show MoreMetadata
Abstract:
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.
Published in: 2019 IEEE Conference on Games (CoG)
Date of Conference: 20-23 August 2019
Date Added to IEEE Xplore: 26 September 2019
ISBN Information: