Abstract: Real Time Strategy games (aka, RTS games) are one of the most popular genres of computer game in the world. Additionally, RTS games are very similar conceptually to simulations of real world strategic problems. However, the study of AI techniques for RTS games and other strategy game variants has been ad hoc when it has been studied at all. In this talk, we will define some of the common traits of strategy games, formulate the problems to be solved, detail existing solutions, and, finally, suggest new areas of research for RTS AI. Examples from several current RTS games, including Empire Earth II, and related real world simulations will illustrate the problems.
Bio: Dr. Ian Lane Davis, former Technical Director at Activision's Santa Monica studio, is widely acknowledged as one of the top artificial intelligence experts in games. His direct game credits include Empire Earth II, Dungeon Siege®: Legends of ArannaTM (2003), Microsoft Game Studios; Empire Earth: The Art of ConquestTM (2002), Sierra Entertainment; Jane's® Attack Squadron (2002), Xicat Interactive; and for Activision Publishing, Inc., Star Trek®: Armada IITM (2001), Call to Power II (2000), Star Trek®: ArmadaTM (2000), Civilization®: Call to PowerTM (1999), Battlezone® (1998), Dark Reign: Rise of the ShadowhandTM (1998), and Dark Reign: The Future of WarTM (1997).
Currently authoring the definitive AI and games textbook for academic and industry training along with academia's top AI researchers, Dr. Davis is a trusted advisor to some of the most important publishers in the industry. Since founding Mad Doc in November 1999, he and his team have provided consulting and game development services for numerous leading publishers, including Vivendi Universal Games, EA Games, Sierra, Midway, Microsoft and Activision.
Dr. Davis is active in the gaming community and serves as a Peer Panel Leader for the Academy of Interactive Arts and Sciences Peer Panel for Gameplay Engineering. Recently appointed as Editor In Chief for the Journal of Game Development Editorial Board, Davis is a highly sought speaker who presents in academic and game focused venues and has been interviewed for online, print and television media. For a comprehensive look at the Doctor's books, publications, speeches and more, visit www.maddocsoftware.com.
Davis earned his doctorate in Artificial Intelligence and Robotics from Carnegie Mellon University, one of the USA's leading computer engineering schools. Here, he applied his talents in Artificial Intelligence to autonomous cross-country navigation in the Highly Mobile Multi-Purpose Wheeled Vehicle (HMMWV) for the Department of Defense, researched the inspection of aging aircraft via the Autonomous NonDestructive Inspector (ANDI) for the FAA, and analyzed and designed systems for the Lunar and Earthbound Lava Tube Explorer.
Abstract: General game players are systems that can accept runtime descriptions of games they have never before seen and, based solely on those descriptions, can play the games effectively without human intervention. Unlike specialized game players, such as Deep Blue, general game players do not rely on algorithms designed in advance for specific games; and, unlike Deep Blue, they are able to play different kinds of games. In this presentation, we look at the technical issues and logistics associated with general game playing and explore the relevance of general game playing to the long-range goals of AI.
Information on the AAAI'05 General Game Player Competition can be found at games.stanford.edu.
Bio: Nathaniel Love is a Ph.D. candidate in computer science at Stanford University. His research interests include computational logic, behavioral constraints, and their applications to both legal and game-playing domains. He earned a B.A. in mathematics and in computer science from Wesleyan University.