Team Sports for Game AI Benchmarking Revisited. (31st May 2021)

• Record Type: Journal Article
• Authors: Mozgovoy, Maxim; Preuss, Mike; Bidarra, Rafael
• Other Names: Katchabaw Michael J. Academic Editor.
• Is Part Of: International journal of computer games technology. Volume 2021(2021)
• Publication Date: 2021-05-31
• Subjects: Computer games -- Design -- Periodicals; Computer games -- Programming -- Periodicals; Jeux d'ordinateur; Jeux d'ordinateur -- Programmation; Computer games -- Design; Computer games -- Programming; Electronic journals; Periodicals; 794.81
• DOI: 10.1155/2021/5521877
• Languages: English
• ISSNs: 1687-7047

Abstract

Abstract : Sport games are among the oldest and best established genres of computer games. Sport-inspired environments, such as RoboCup, have been used for AI benchmarking for years. We argue that, in spite of the rise of increasingly more sophisticated game genres, team sport games will remain an important testbed for AI benchmarking due to two primary factors. First, there are several genre-specific challenges for AI systems that are neither present nor emphasized in other types of games, such as team AI and frequent replanning. Second, there are unmistakable nonskill-related goals of AI systems, contributing to player enjoyment, that are most easily observed and addressed within a context of a team sport, such as showing creative and emotional traits. We analyze these factors in detail and outline promising directions for future research for game AI benchmarking, within a team sport context.