Team Sports for Game AI Benchmarking Revisited
| Autor: | Mozgovoy, M., Preuss, M., Bidarra, R., Katchabaw Michael J. |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Knowledge management
Article Subject Team sport Computer science business.industry Testbed ComputingMilieux_PERSONALCOMPUTING Context (language use) 02 engineering and technology Benchmarking Computer Graphics and Computer-Aided Design GeneralLiterature_MISCELLANEOUS Human-Computer Interaction QA76.75-76.765 020204 information systems 0202 electrical engineering electronic engineering information engineering Spite 020201 artificial intelligence & image processing Computer software business Software Ai systems |
| Zdroj: | International Journal of Computer Games Technology, Vol 2021 (2021) International Journal of Computer Games Technology, 2021 International Journal of Computer Games Technology, 2021, 1-9. Hindawi Limited |
| ISSN: | 1687-7055 1687-7047 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text