Generating Diverse and Competitive Play-Styles for Strategy Games
This addresses the problem of creating varied and strong AI opponents for strategy games, which is incremental as it builds on existing methods like Monte Carlo Tree Search and quality-diversity algorithms.
The paper tackles the challenge of designing AI agents that maintain competitive play while exhibiting diverse play-styles in strategy games, demonstrating that their algorithm achieves these goals across extensive game levels beyond training.
Designing agents that are able to achieve different play-styles while maintaining a competitive level of play is a difficult task, especially for games for which the research community has not found super-human performance yet, like strategy games. These require the AI to deal with large action spaces, long-term planning and partial observability, among other well-known factors that make decision-making a hard problem. On top of this, achieving distinct play-styles using a general algorithm without reducing playing strength is not trivial. In this paper, we propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes) and show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play. Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.