Generating Diverse and Competitive Play-Styles for Strategy Games

TL;DR

This paper introduces a novel AI method combining Portfolio Monte Carlo Tree Search with Progressive Unpruning and MAP-Elites to generate diverse, competitive play-styles in complex strategy games like Tribes, addressing the challenge of style diversity without sacrificing strength.

Contribution

It presents a new algorithm that produces multiple distinct play-styles in strategy games while maintaining high performance, a significant advancement over prior single-style approaches.

Findings

The algorithm successfully generates diverse play-styles across various game levels.

It maintains competitive performance comparable to state-of-the-art agents.

The approach generalizes well beyond training levels, demonstrating robustness.

Abstract

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.