Computers and Games 2022

Welcome to the home page for the Computers and Games 2022 conference. This conference is 20 years old and is held in even-numbered years (Advances in Computer Games is in the odd-numbered years). It originated in Japan and is now organized by the International Computer Games Association.

CG features cutting edge artificial intelligence technology as applied to computer games. This year’s conference is being held online November 22-24. It features four outstanding keynote talks and 15 refereed papers.

The conference co-chairs are:

Cameron Browne, Maastricht University, The Netherlands
Akihiro Kishimoto, IBM Research, Tokyo, Japan

UPDATE: The conference proceedings have been published! Find out more here.

Registering for the Conference

Conference attendee registration is free. A few days before the conference you will receive a video link which will allow you to watch and interact with the live presentations.

Please register here.

Schedule

Day 1 (North America friendly times)
10:50 Nov 22-16:00 Nov 22 in Edmonton (MST);
09:50 Nov 22-15:00 Nov 22 in California (PST);
12:50 Nov 22-18:00 Nov 22 in New York (EST);
18:50 Nov 22 -00:00 Nov 23 in Amsterdam (CET);
02:50 Nov 23-08:00 Nov 23 in Tokyo (JST)
Day 2 (Asia friendly times)
22:00 Nov 23-01:40 Nov 24 in Edmonton (MST);
21:00 Nov 23-00:40 Nov 24 in California (PST);
00:00 Nov 24-03:40 Nov 24 in New York (EST);
06:00 Nov 24-09:40 Nov 24 in Amsterdam (CET);
14:00 Nov 24-17:40 Nov 24 in Tokyo (JST)
Day 3 (Europe friendly times)
07:00 Nov 24-10:00 Nov 24 in Edmonton (MST);
06:00 Nov 24-09:00 Nov 24 in California (PST);
09:00 Nov 24-12:00 Nov 24 in New York (EST);
15:00 Nov 24-18:00 Nov 24 in Amsterdam (CET);
23:00 Nov 24-02:00 Nov 25 in Tokyo (JST);

Click here for the detailed schedule.

Keynote Speakers

Murray Campbell (IBM T.J. Watson)

The Evolving Role of Games in AI

Games have been popular domains for artificial intelligence research since the earliest days of the field. In this talk I will review the evolution of the role of games in AI and offer some ideas on the future roles that games can play as we take aim at building more general AI systems.

Murray Campbell is a Distinguished Research Scientist at the IBM T.J. Watson Research Center. His current research focus is in the area of neuro-symbolic artificial intelligence. In earlier work, Murray was a member of the team that developed Deep Blue, the first computer to defeat the reigning world chess champion in a regulation match.

Matt Ginsberg (Google X)

What I Learned from Dr.Fill

From 2012 through 2021, a computer program that I wrote called Dr.Fill participated in the American Crossword Puzzle Tournament, the premier crossword solving event in the world. In 2021, it won, thereby adding crosswords to the list of games at which computers outperform humans. This (primarily) nontechnical talk describes what this journey taught me – about search, about machine learning and large language models, about crosswords themselves, and about managing human interactions while displacing human champions at this very human pastime.

Matt Ginsberg got a doctorate in astrophysics from Oxford when he was 24. He quickly came to his senses, however, switching to artificial intelligence and teaching at Stanford for a decade. He’s been on the front page of the New York Times and, surprisingly, was happy about it. He’s been a political columnist and published playwright, and constructs crosswords for the Times. He has written about a hundred technical papers. And one novel.

Tao Qin (Microsoft Research AI4Science)

Deep Reinforcement Learning for Game Playing and Testing

Powered by recent advances of deep learning and reinforcement learning, game AI has made remarkable progress in recent years. In this talk, I will present two of our recent projects on deep RL for game playing and testing. (1) Project Suphx: the World-Best Mahjong AI, which demonstrated stronger performance than most top human players in terms of stable rank and is rated above 99.99% of all the officially ranked human players in the Tenhou platform. This is the first time that a computer program achieves 10 DAN and outperforms most top human players in Mahjong. (2) Project Mariana: Pixel based AI for Automated Game Testing. We built a general game testing agent, Inspector, that is only based on screenshots/pixels and can be easily applied to different games without deep integration with games.

Dr. Tao Qin is a Senior Principal Researcher at Microsoft Research AI4Science. His research interests include deep learning (with applications to scientific discovery, machine translation, speech synthesis and recognition), reinforcement learning (with applications to games and real-world problems), and game theory and multi-agent systems (with applications to cloud computing, online and mobile advertising). His team won the first place for 8 translation tasks in WMT 2019, built the world-best Mahjong AI, named Suphx, which achieved 10 DAN on the Tenhou platform in 2019, and developed the FastSpeech series models supporting 100+ languages and 300+ voices in Azure TTS.

Olivier Teytaud (Meta AI Research)

AI and Games: New Directions

After many visible successes in board, video and card games, AI becomes critical in games involving language, virtual reality, interaction, understanding or creating text or vision. We will see how, thanks to versatile solutions involving or combining all these fields and taking into account that users are humans, games remains both an enormous industry and a platform for preparing other applications.

Olivier Teytaud studied at ENS Lyon, Lyon, France. He received the Ph.D. degree from University Lyon 2 in 2001. He is a Research Scientist with Facebook AI Research, Paris, France. He has been working in power systems, arithmetics, games, control, optimization, and computer vision. He currently contributes to Nevergrad, a platform for derivative-free optimization, and Polygames, which recently won the first games against a top level player in the game of Hex and in the game of Havannah.

Accepted Papers

4895 Xavier Blanvillain. Oware is Strongly Solved
5845 Todd Neller and Taylor Neller. FairKalah: Towards Fair Mancala Play
4010 Owen Randall, Ting-Han Wei, Ryan Hayward and Martin Müller. Improving Search in Go Using Bounded Static Safety
6388 Yifan He and Abdallah Saffidine. QBF solving using Best First Search
5628 Tristan Cazenave. Batch Monte Carlo Tree Search
8996 Jos Uiterwijk and Lianne Hufkens. Solving Impartial SET using Knowledge and Combinatorial Game Theory
3778 Cameron Browne. Which Rules for Mu Torere?
5135 Stefan Edelkamp. Improving Computer Play in Skat with Hope Cards
6011 Matthew Stephenson, Dennis J. N. J. Soemers, Eric Piette and Cameron Browne. Measuring Board Game Distance
6383 Daniel Collins. Solving Chainmail Jousting
6430 Nathan Sturtevant. Chinese Checkers Bitboards for Move Generation and Ranking Using Bitboards and BMI2 pext and pdep Instructions
2958 Kyle Sacks and Brayden Hollis. An Algorithm for Multiplayer Games Exploiting Opponents’ Interactions with the Player
7302 Thijs Laarhoven and Aditya Ponukumati. Human and Computer Decision-Making in Chess with Applications to Online Cheat Detection
8029 Nathan Lervold, Gilbert Peterson and David King. Incentivizing Information Gain in Hidden Information Multi-Action Games
3876 Gaspard de Batz de Trenquelleon, Ahmed Choukarah, Milo Roucairol, Maël Addoum and Tristan Cazenave. Procedural Generation of Rush Hour Levels

Conference Talk Videos

Program Committee

Bruno Bouzy, Nukkai
Tristan Cazenave, LAMSADE Université Paris Dauphine PSL CNR
Lung-Pin Chen, Tunghai University
Reijer Grimbergen, Tokyo University of Technology
Michael Hartisch, University of Siegen
Ryan Hayward, University of Alberta
Chu-Hsuan Hsueh, Japan Advanced Institute of Science and Technology
Hiroyuki Iida, Japan Advanced Institute of Science and Technology
Nicolas Jouandeau, Paris8 University
Tomoyuki Kaneko, The University of Tokyo
Jakub Kowalski, University of Wroc?aw
Sylvain Lagrue, Université de Technologie de Compiègne (UTC)
Diego Perez Liebana, Queen Mary University of London
Martin Mueller, University of Alberta
Todd Neller, Gettysburg College
Mark J. Nelson, American University
Eric Piette, DKE
Spyridon Samothrakis, University of Essex
Jonathan Schaeffer, University of Alberta
Dennis J. N. J. Soemers, Maastricht University
Matthew Stephenson, Maastricht University
Nathan Sturtevant, University of Alberta
Ruck Thawonmas, Ritsumeikan University
Michael Thielscher, University of New South Wales
Jonathan K. Vis, Leiden, University Medical Center
Kazuki Yoshizoe, Kyushu University
Ting Han Wei, University of Alberta
Mark H. M. Winands, Maastricht University
I-Chen Wu, National Chiao Tung University

Contact

Questions about submissions should be emailed to cg2022@easychair.org.

International Computer Games Association (ICGA)

Interested in AI and games? Join the ICGA! Membership allows you to:

Receive the quarterly ICGA Journal (electronically or in print).
Enter the World Computer Chess Championships.
Enter the Computer Olympiad.
Contribute to and/or participate in the annual Computers and Games and Advances in Computer Games conferences.
Join an international community of researchers/companies/hobbyists who have a passion for applying to AI to games.

For more information, please go here.

Call for Papers

Areas of Interest

Areas of interest include, but are not limited to:

The current state of game-playing programs for classic and modern board games, card games, puzzles, virtual/casual/video games, etc.
General game playing
Artificial intelligence and machine learning for games
The history of computers in game-based research
New theoretical developments in game-related research
New and enhanced algorithms for search and knowledge acquisition
Automated game design and evaluation
Social aspects of computer games
Scientific contributions produced by the study of games
Cognitive research of how (and why) humans play games and puzzles
Capture and analysis of game data
Innovative applications of game-AI algorithms

Submission Guidelines

Papers must be written in English and can be up to 10 pages in length (including references). Please conform to the LNCS style. LaTeX preferred; an Overleaf template is available here. Submit a PDF version of your paper via EasyChair.

Dates

~~September 1~~ ~~September 8~~ September 12: Submission deadline (extended)
October 17: Decisions announced
November 7: Final version due
November 22-24: Computers and Games 2022 conference