Thawonmas, Ruck, Julian Togelius, and Georgios N. Yannakakis. “Artificial general intelligence in games: Where play meets design and user experience.” In NII Shonan Meeting , no. 130. 2019.
URL1 URL2
Arguably the grand goal of artificial intelligence (AI) research is to produce machines that can solve multiple problems, not just one. Until recently, almost all research projects in the game
AI field, however, have been very specific in that they focus on one particular way in which intelligence can be applied to video games. Most published work describes a particular method—or a comparison of two or more methods—for performing a single task in a single game. If an AI approach is only tested on a single task for a single game, how can we argue that such a practice advances the scientific study of AI? And how can we argue that it is a useful method for a game designer or developer, who is likely working on a completely different game than the method was tested on? This Shonan meeting aims to discuss three aspects on how to generalize AI in games: how to play any games, how to model any game players, and how to generate any games, plus their potential applications. The meeting consists of 17 discussions on relevant topics. Findings of this meeting can be found in the discussions’ abstracts, which include overviews of respective topics, highlights of research questions, their potential answers, and future directions.