The IJCAI-09 Workshop on General Game Playing
General Intelligence in Game-Playing Agents (GIGA'09)
News
-
The GIGA'09 schedule is available (here). The paper presentations take place on Monday July 13th. Each talk will be allotted a 25-minute slot: 17 minutes for the presentation and 8 minutes for questions.
- Although not a part of the workshop, we want to draw to your attention that a GGP tutorial New Trends in General Game Playing will be held on Sunday July 12.
- This year's GGP competition will be held in association with the GIGA'09 workshop on Saturday July 11th. Posters describing the participating agents will be on display. For details please visit the competition page (here).
General Information
Artificial Intelligence (AI) researchers have for decades worked on building game-playing agents capable of matching wits with the strongest humans in the world, resulting in several success stories for games like e.g. chess and checkers. The success of such systems has been for a part due to years of relentless knowledge-engineering effort on behalf of the program developers, manually adding application-dependent knowledge to their game-playing agents. Also, the various algorithmic enhancements used are often highly tailored towards the game at hand.Research into general game playing (GGP) aims at taking this approach to the next level: to build intelligent software agents that can, given the rules of any game, automatically learn a strategy for playing that game at an expert level without any human intervention. On contrary to software systems designed to play one specific game, systems capable of playing arbitrary unseen games cannot be provided with game-specific domain knowledge a priory. Instead they must be endowed with high-level abilities to learn strategies and make abstract reasoning. Successful realization of this poses many interesting research challenges for a wide variety of artificial-intelligence sub-areas including (but not limited to):
- knowledge representation,
- reasoning,
- heuristic search,
- automated planning,
- computational game-theory,
- multi-agent systems, and
- machine learning.
The aim of this workshop is bring together researchers from the above sub-fields of AI to discuss how best to address the challenges of and further advance the state-of-the-art of general game-playing systems and generic artificial intelligence.
Call for Papers
Call for papers: [ PDF ]
If you are interesting in attending the conference without submitting a paper please send a short statement of interest to one of the contact organizers listed below before April 17th.
Information for Authors
The workshop papers should be submitted online using the EasyChair system (click here). Submitted papers must adhere to the IJCAI-09 paper-formatting guidelines and not to exceed 8 pages, including all figures and references. Note though that paper submissions to the workshop are not to be anonymous. The papers must present original work that has not been published elsewhere. However, we allow submission of papers that are under review elsewhere, in particular we welcome papers submitted to the main technical track of IJCAI. All papers will be peer reviewed.
Important dates:
Non-archival working notes will be produced containing the papers presented at the workshop.
Workshop Organizers
-
Yngvi Björnsson (contact person)
School of Computer Science
Reykjavik University
Email:
-
Peter Stone
Department of Computer Sciences
University of Texas at Austin
-
Michael Thielscher (contact person)
Department of Computer Science
Dresden University of Technology
Email:
Program Committee
- Yngvi Björnsson, Reykjavik University
- Patrick Doherty, Linköping University
- Michael Genesereth, Stanford University
- Jonathan Schaeffer, University of Alberta
- Peter Stone, University of Texas
- Michael Thielscher, Dresden University of Technology
- Jaap van den Herik, Tilburg University
- Michael Wooldridge, University of Liverpool
Links
