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.
翻译:设计代理人既能达到不同的游戏风格,同时又能保持竞争性的游戏水平是一项艰巨的任务,特别是对于研究界尚未发现超人表现的游戏来说,就像战略游戏一样。这要求AI处理大型行动空间、长期规划和部分可观测性,以及使决策成为难题的其他众所周知的因素。此外,在这一点上,使用通用算法实现不同的游戏风格而不降低游戏强度并不是微不足道的。在本文中,我们建议Portfolio Monte Carlo Tree搜索(Search)以渐进方式启动一个以转盘为基础的战略游戏(Tribes),并展示它如何被参数化,以便使用一个质量多样性算法(MAP-Elites)实现不同的游戏风格,同时保持竞争的游戏水平。我们的结果表明,这种算法能够实现这些目标,甚至为了广泛收集超出培训使用的游戏水平的游戏水平。