NO.130 Artificial General Intelligence in Games: Where Play Meets Design and User Experience
March 18 - 21, 2019 (Check-in: March 17, 2019 )
- Ruck Thawonmas
- Ritsumeikan University, Japan
- Julian Togelius
- New York University, USA
- Georgios Yannakakis
- University of Malta, Malta
Description of the meeting
Arguably the grand goal of artificial intelligence research is to produce machines with general intelligence or artificial general intelligence: the capacity to solve multiple problems, not just one. Artificial intelligence (AI) has investigated the general intelligence capacity of machines within the domain of games more than any other domain given the ideal properties of games, for that purpose: controlled yet interesting and computationally hard problems. By now, an active and healthy research community around computational and artificial intelligence (AI) in games has existed for more than a decade — at least since the start of the IEEE Conference on Computational Intelligence and Games (CIG) and the Artificial Intelligence and Interactive Digital Entertainment (AIIDE) conference series in 2005. Before then, research has been ongoing about AI in board games since the dawn of automatic computing. Initially, most of the work published at IEEE CIG or AIIDE was concerned with learning to play a particular game as well as possible, or using search/planning algorithms to play a game as well as possible without learning. Gradually, a number of new applications for AI in games and for games in AI have come to complement the original focus on AI for playing games. Papers on procedural content generation, player modeling, game data mining, human-like playing behavior, automatic game testing and so on have become commonplace within the community. Games, some popular titles of which have been recently proven to be NP-hard or PSPACE-complete, appear to be an ideal domain for realizing several long-standing goals of AI including affective computing, computational creativity and ultimately general intelligence. Additionally, the digital games industry is economically important, growing rapidly and dependent on advances in AI methods tailored to game.
Almost all research projects in the game AI field, however, are very specific in that they focus on one particular way in which intelligence can be applied to games. Most published work describes a particular method—or a comparison of two or more methods—for performing a single task (playing, modeling, generating etc.) in a single game. This is problematic in several ways, both for the scientific value and for the practical applicability of the methods developed and studies made in the field. If an AI approach is only tested on a single task for a single game, how can we argue that is an advance in the scientific study of artificial intelligence? 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?
The proposed Shonan meeting aims to discuss how we can take the general game-playing paradigm and expand it to cater for all core AI tasks within a game design process. That includes general player experience and behavior modeling, general non-player character behavior, general AI-assisted tools, general level generation and complete game generation; some of the key areas are described in further detail in the sections below. The new scope for artificial general intelligence in games beyond game-playing broadens the applicability and capacity of AI algorithms and our understanding of intelligence as tested in a creative domain that interweaves problem solving, art, and engineering. For the purposes of furthering this line of research, we will invite experts in various areas of AI related to games to discuss how their research can influence this new paradigm.
General Game Playing: The problem of AI playing games is the one that has been most generalized so far. There already exist at least three serious benchmarks or competitions attempting to pose the problem of playing games in general, each in its own imperfect way: the General Game Playing Competition, the Arcade Learning Environment (ALE) and the General Video Game AI Competition (GVGAI). The results from these competitions so far indicate that general purpose search and learning algorithms by far outperform more domain-specific solutions and “clever hacks”. This is a very marked difference to the results of the game-specific competitions, which as discussed above tend to favor domain-specific solutions. While these are each laudable initiatives and currently the focus of much research, in the future we will need to expand the scope of these competitions and benchmarks considerably, including expanding the range of games available to play and the conditions under which gameplay happens.
Beyond playing characters one would expect that non-player characters in games would be able to perform well under any context and game (seen or unseen) in similar ways humans do. Not only would that be a far more effective approach for agent modeling but it would also advance our understanding about general emotive, social and behavioral patterns. However, as with the other uses of AI in games, the construction of agent architectures for behavior modeling and expression is heavily dependent on particular game contexts and specific to (and optimized for) a particular game. One vision whose potential we wish to explore in this Shonan meeting is the creation of general NPCs, that could easily be dropped into any given game and adapt (autonomously and/or with designer guidance) to the requirements of a particular game, so that they can behave believably and effectively in their new context.
General Player Models: Evidence from neuroscience and experimental psychology suggest that general intelligence implies (and is tightly coupled with) socioemotional intelligence. The ability to recognize human behavior and emotion is a complex yet critical task for human communication. Throughout evolution, we have developed particular forms of advanced cognitive, emotive and social skills to address this challenge. Beyond these skills, we also have the capacity to detect affective patterns across people with different moods, cultural backgrounds and personalities. This generalization ability also extends, to a degree, across contexts and social settings.
For AI in games to be general beyond game-playing it needs to be able to recognize general socioemotional and cognitive/behavioral patterns. This is essentially AI that can detect context-free emotive and cognitive reactions and expressions across context and builds general computational models of human behavior and experience which are grounded in a general golden standard of human behavior. So far we have only seen a few proof-of-concept studies in this direction.
General Game Generation: The study of procedural content generation (PCG) for the design of game levels has reached a certain extent of maturity and is, by far, the most popular domain for the application of PCG algorithms and approaches. As with the other sub-tasks of game design discussed above we argue that there needs to be a shift in how game generation is viewed. The obvious change of perspective is to create general game generators—game generators with general intelligence. That would mean that levels, audio, game narrative etc. are generated successfully across game genres and players and that the output of the generation process is a that is meaningful and playable well as entertaining for the player and/or the spectator. Further, a general game generator should be able to coordinate the generative process with the other computational game designers who are responsible for the other parts of the game design.