Team Sports for Game AI Benchmarking Revisited

Maxim Mozgovoy, Mike Preuss, Rafael Bidarra

Research output: Contribution to journalArticleScientificpeer-review

33 Downloads (Pure)

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.

Original languageEnglish
Article number5521877
Pages (from-to)1-9
Number of pages9
JournalInternational Journal of Computer Games Technology
Volume2021
DOIs
Publication statusPublished - 2021

Fingerprint

Dive into the research topics of 'Team Sports for Game AI Benchmarking Revisited'. Together they form a unique fingerprint.

Cite this