Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Overview
Objective of Reasoning
Search Method of Fluxplayer
Search Method of Fluxplayer 37
Overview of the Complete Method
The General Proof Method and Its Correctness
Experimental Results
Summary and Outlook
Theoretic Results
Related Work
Chapter 9. Related Work
Material Value
Summary
Summary 135
Discussion
Future Work
References

Knowledge-Based General Game Playing

Profile image of Stephan SchiffelStephan Schiffel

2011, Künstliche Intelligenz

https://doi.org/10.1007/S13218-010-0073-8
visibility

…

description

161 pages

link

1 file

Abstract

Although we humans cannot compete with computers at simple brute-force search, this is often more than compensated for by our ability to discover structures in new games and to quickly learn how to perform highly selective, informed search. To attain the same level of intelligence, general game playing systems must be able to figure out, without human assistance, what a new game is really about. This makes General Game Playing in ideal testbed for human-level AI, because ultimate success can only be achieved if computers match our ability to master new games by acquiring and exploiting new knowledge. This article introduces five knowledge-based methods for General Game Playing. Each of these techniques contributes to the ongoing success of our FLUXPLAYER (Schiffel and Thielscher in Proceedings of the National Conference on Artificial Intelligence, pp. 1191–1196, 2007), which was among the top four players at each of the past AAAI competitions and in particular was crowned World Champion in 2006.

Related papers

General game playing: Overview of the AAAI competition
Barney Pell, Michael Genesereth

AI magazine, 2005

A General Game Playing System is one that can accept a formal description of a game and play the game 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 order to promote work in this area, the AAAI is sponsoring an open competition at this summer's National Conference. This article is an overview of the technical issues and logistics associated with this summer's competition, as well as the relevance of General Game Playing to the long range goals of artificial intelligence.

View PDFchevron_right
Towards Cognitively Plausible Game Playing Systems
Jacek Mandziuk

IEEE Computational Intelligence Magazine, 2000

We propose to return to the roots of Artificial/Computational Intelligence applicability to board games domain by attempting to mimic human way of playing (or human intelligence in a broader perspective). The paper provides the argumentation for potential virtues of developing cognitively-plausible pattern-based human-like playing systems. Such systems, besides playing games, may in principle, also be applied to other domains related to general problem-solving.

View PDFchevron_right
Computational Intelligence and AI in Games: A New IEEE Transactions
Simon Lucas

2009

Games have long been seen as an ideal test-bed for the study of AI. Until recently, most of the academic work in the area focused on traditional board games and card games, the challenge being to beat expert human players. Following the release of Pong in the early 1970s, the last few decades have seen a phenomenal increase in the quality, diversity and pervasiveness of video games.

View PDFchevron_right
A Survey of Planning and Learning in Games
Luis Paulo Reis

Applied Sciences

In general, games pose interesting and complex problems for the implementation of intelligent agents and are a popular domain in the study of artificial intelligence. In fact, games have been at the center of some of the most well-known achievements in artificial intelligence. From classical board games such as chess, checkers, backgammon and Go, to video games such as Dota 2 and StarCraft II, artificial intelligence research has devised computer programs that can play at the level of a human master and even at a human world champion level. Planning and learning, two well-known and successful paradigms of artificial intelligence, have greatly contributed to these achievements. Although representing distinct approaches, planning and learning try to solve similar problems and share some similarities. They can even complement each other. This has led to research on methodologies to combine the strengths of both approaches to derive better solutions. This paper presents a survey of the ...

View PDFchevron_right
Automatic heuristic construction in a complete general game player
Peter Stone

2006

Abstract Computer game players are typically designed to play a single game: today's best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing an agent capable of playing many different previously unseen games. The first AAAI General Game Playing Competition was held at AAAI 2005 in order to promote research in this area. In this article, we survey some of the issues involved in creating a general game playing system and introduce our entry to that event.

View PDFchevron_right
CI in General Game Playing - To Date Achievements and Perspectives
Jacek Mandziuk

Lecture Notes in Computer Science, 2010

Multigame playing agents are programs capable of autonomously learning to play new, previously unknown games. In this paper, we concentrate on the General Game Playing Competition which defines a universal game description language and acts as a framework for comparison of various approaches to the problem. Although so far the most successful GGP agents have relied on classic Artificial Intelligence approaches, we argue that it would be also worthwhile to direct more effort to construction of General Game Players based on Computational Intelligence methods. We point out the most promising, in our opinion, directions of research and propose minor changes to GGP in order to make it a common framework suited for testing various aspects of multigame playing.

View PDFchevron_right
Artificial and Computational Intelligence in Games (Dagstuhl Seminar 12191)}}
Simon Lucas

Abstract This report documents the program and the outcomes of Dagstuhl Seminar 12191" Artificial and Computational Intelligence in Games". The aim for the seminar was to bring together creative experts in an intensive meeting with the common goals of gaining a deeper understanding of various aspects of artificial and computational intelligence in games, to help identify the main challenges in game AI research and the most promising venues to deal with them.

View PDFchevron_right
General Board Game Playing for Education and Research in Generic AI Game Learning
Wolfgang Konen

2019 IEEE Conference on Games (CoG)

We present a new general board game (GBG) playing and learning framework. GBG defines the common interfaces for board games, game states and their AI agents. It allows one to run competitions of different agents on different games. It standardizes those parts of board game playing and learning that otherwise would be tedious and repetitive parts in coding. GBG is suitable for arbitrary 1-, 2-,. .. , N-player board games. It makes a generic TD(λ)-n-tuple agent for the first time available to arbitrary games. On various games, TD(λ)-n-tuple is found to be superior to other generic agents like MCTS. GBG aims at the educational perspective, where it helps students to start faster in the area of game learning. GBG aims as well at the research perspective by collecting a growing set of games and AI agents to assess their strengths and generalization capabilities in meaningful competitions. Initial successful educational and research results are reported.

View PDFchevron_right
Generic Heuristic Approach to General Game Playing
Jacek Mandziuk

2012

General Game Playing (GGP) is a specially designed environment for creating and testing competitive agents which can play variety of games. The fundamental motivation is to advance the development of various artificial intelligence methods operating together in a previously unknown environment. This approach extrapolates better on real world problems and follows artificial intelligence paradigms better than dedicated single-game optimized solutions. This paper presents a universal method of constructing the heuristic evaluation function for any game playable within the GGP framework. The algorithm embraces distinctive discovery of candidate features to be included in the evaluation function and learning their correlations with actions performed by the players and the game score. Our method integrates well with the UCT algorithm which is currently the state-of-the-art approach in GGP.

View PDFchevron_right
Simulation-based approach to general game playing
Yngvi Björnsson

The Twenty-Third AAAI Conference on Artificial …, 2008

The aim of General Game Playing (GGP) is to create intelligent agents that automatically learn how to play many different games at an expert level without any human intervention. The most successful GGP agents in the past have used traditional game-tree search combined with an automatically learned heuristic function for evaluating game states. In this paper we describe a GGP agent that instead uses a Monte Carlo/UCT simulation technique for action selection, an approach recently popularized in computer Go. Our GGP agent has proven its effectiveness by winning last year's AAAI GGP Competition. Furthermore, we introduce and empirically evaluate a new scheme for automatically learning search-control knowledge for guiding the simulation playouts, showing that it offers significant benefits for a variety of games.

View PDFchevron_right

References (93)

  1. Krzysztof Apt, H. A. Blair, and A. Walker. Towards a theory of declarative knowledge. In J. Minker, editor, Foundations of Deductive Databases and Logic Programming, chapter 2, pages 89-148.
  2. Morgan Kaufmann, 1987.
  3. Fadi A. Aloul, Arathi Ramani, Igor L. Markov, and Karem A. Sakallah. Solving difficult sat instances in the presence of symmetry. In Design Automation Conference. University of Michigan, June 2002.
  4. Blai Bonet and Hector Geffner. Planning as heuristic search. Artificial Intelligence, 129(1-2):5-33, 2001.
  5. Bikramjit Banerjee, Gregory Kuhlmann, and Peter Stone. Value function transfer for general game playing. In ICML workshop on Structural Knowledge Transfer for Machine Learning, 2006.
  6. Encyclopaedia Britannica. Game. http://www.britannica.com/ EBchecked/topic/224863/game, January 2011.
  7. Bikramjit Banerjee and Peter Stone. General game learning using knowledge transfer. In The 20th International Joint Conference on Artificial Intelligence, pages 672-677, 2007.
  8. Michael Buro. From simple features to sophisticated evaluation functions. In CG '98: Proceedings of the First International Conference on Computers and Games, pages 126-145, London, UK, 1999. Springer-Verlag.
  9. Keith Clark. Negation as failure. In H. Gallaire and J. Minker, editors, Logic and Data Bases, pages 293-322. Plenum Press, 1978.
  10. James Clune. Heuristic evaluation functions for general game playing. In Proceedings of the National Conference on Artificial Intelligence, pages 1134-1139, Vancouver, July 2007. AAAI Press.
  11. James Clune. Heuristic Evaluation Functions for General Game Playing. PhD thesis, University of California, Los Angeles, 2008.
  12. Rémi Coulom. Efficient selectivity and backup operators in monte- carlo tree search. In Proceedings of the 5th international conference on Computers and games, CG'06, pages 72-83, Berlin, Heidelberg, 2007. Springer-Verlag.
  13. Constantinos Daskalakis, Paul W. Goldberg, and Christos H. Papadimitriou. The complexity of computing a nash equilibrium. 146 BIBLIOGRAPHY In Proceedings of the thirty-eighth annual ACM symposium on Theory of computing, STOC '06, pages 71-78, New York, NY, USA, 2006. ACM.
  14. Jarno Elonen. Nanohttpd, 2010. http://elonen.iki.fi/code/nanohttpd/.
  15. Tom E. Fawcett. Feature Discovery for Problem Solving Systems. PhD thesis, University of Massachusetts, Amherst, 1993.
  16. Tom E. Fawcett. Knowledge-based feature discovery for evaluation functions. Computational Intelligence, 12(1):42-64, 1996.
  17. Hilmar Finnsson and Yngvi Björnsson. Simulation-based approach to general game playing. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 259-264, Chicago, July 2008. AAAI Press.
  18. Hilmar Finnsson and Yngvi Björnsson. Learning simulation control in general game playing agents. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 954-959, Atlanta, July 2010. AAAI Press.
  19. Hilmar Finnsson and Yngvi Björnsson. Cadiaplayer: Search-control techniques. KI, 25(1):9-16, 2011.
  20. Maria Fox and Derek Long. The detection and exploitation of symmetry in planning problems. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 956-961, 1999.
  21. M. Fox and D. Long. Extending the exploitation of symmetries in planning. In Proceedings of AIPS'02, 2002.
  22. Michael Gelfond. Answer sets. In F. van Harmelen, V. Lifschitz, and B. Porter, editors, Handbook of Knowledge Representation, pages 285-316. Elsevier, 2008.
  23. M. Genesereth. Knowledge interchange format, 1998.
  24. Michael Gelfond and Vladimir Lifschitz. The stable model seman- tics for logic programming. In R. Kowalski and K. Bowen, editors, Proceedings of the International Joint Conference and Symposium on Logic Programming (IJCSLP), pages 1070-1080, Seattle, OR, 1988. MIT Press.
  25. Michael R. Genesereth, Nathaniel Love, and Barney Pell. General game playing: Overview of the aaai competition. AI Magazine, 26(2):62-72, 2005.
  26. Martin Günther, Stephan Schiffel, and Michael Thielscher. Factor- ing general games. In Yngvi Björnsson, Peter Stone, and Michael Thielscher, editors, Proceedings of the IJCAI-09 Workshop on Gen- eral Game Playing (GIGA'09), pages 27-34, Pasadena, California, USA, July 2009.
  27. Martin Günther. Decomposition of single player games. Großer Beleg, TU-Dresden, 2007.
  28. Martin Günther. Automatic feature construction for general game playing. Master's thesis, Technische Universität Dresden, 2008.
  29. Sylvain Gelly, Yizao Wang, Rémi Munos, and Olivier Teytaud. Modification of UCT with Patterns in Monte-Carlo Go. Research Report RR-6062, INRIA, 2006.
  30. Sebastian Haufe, Daniel Michulke, Stephan Schiffel, and Michael Thielscher. Knowledge-based general game playing. KI, 25(1):25- 33, 2011.
  31. Jörg Hoffmann and Bernhard Nebel. The ff planning system: Fast plan generation through heuristic search. Journal of Artificial Intelligence Research, 14:253-302, 2001.
  32. Peter Hart, Nils Nilsson, and Bertram Raphael. A formal basis for the heuristic determination of minimum cost paths. IEEE Transactions on Systems Science and Cybernetics, 4:100-107, 1968.
  33. David M. Kaiser. Automatic feature extraction for autonomous general game playing agents. In Proceedings of the Sixth Inter- national Joint Conference on Autonomous Agents and Multiagent Systems, 2007.
  34. David M. Kaiser. The design and implementation of a successful general game playing agent. In The Florida AI Research Society Conference, pages 110-115, 2007.
  35. David M. Kaiser. The Structure Of Games. PhD thesis, Florida International University, Miami, 2007.
  36. Gregory Kuhlmann, Kurt Dresner, and Peter Stone. Automatic heuristic construction in a complete general game player. In Proceedings of the Twenty-First National Conference on Artificial Intelligence, pages 1457-62. AAAI Press, July 2006.
  37. Peter Kissmann and Stefan Edelkamp. Instantiating general games. In Yngvi Björnsson, Peter Stone, and Michael Thielscher, editors, Proceedings of the IJCAI-09 Workshop on General Game Playing (GIGA'09), Pasadena, California, USA, July 2009.
  38. Peter Kissmann and Stefan Edelkamp. Gamer, a general game playing agent. KI, 25(1):49-52, 2011.
  39. Rudolf Kruse, Jörg Gebhardt, and Frank Klawonn. Fuzzy-Systeme. Teubner, 1995.
  40. Richard E. Korf. Real-time heuristic search. Artificial Intelligence, 42(2-3):189-211, 1990.
  41. Levente Kocsis and Csaba Szepesvári. Bandit based monte-carlo planning. In In: ECML-06. Number 4212 in LNCS, pages 282-293. Springer, 2006.
  42. Gregory Kuhlmann and Peter Stone. Graph-based domain mapping for transfer learning in general games. In Proceedings of The European Conference on Machine Learning, September 2007.
  43. Mesut Kirci, Nathan R. Sturtevant, and Jonathan Schaeffer. A ggp feature learning algorithm. KI, 25(1):35-42, 2011.
  44. Gregory John Kuhlmann. Automated Domain Analysis and Trans- fer Learning in General Game Playing. PhD thesis, University of Texas at Austin, 2010.
  45. Kevin Leyton-Brown. Essentials of Game Theory: A Concise, Multidisciplinary Introduction (Synthesis Lectures on Artificial In- telligence and Machine Learning). Morgan and Claypool Publishers, 1 edition, June 2008.
  46. D. Long and M. Fox. Symmetries in planning problems. In Proceedings of SymCon'03 (CP Workshop), 2003.
  47. LHH + 08] Nathaniel Love, Timothy Hinrichs, David Haley, Erik Schkufza, and Michael Genesereth. General game playing: Game description language specification. Technical Report LG-2006-01, Stanford Logic Group, Computer Science Department, Stanford University, 353 Serra Mall, Stanford, CA 94305, March 2008. Available at: games.stanford.edu.
  48. Carol Luckhart and Keki B. Irani. An algorithmic solution of n-person games. In Fifth National Conference of the American Association for Artificial Intelligence (AAAI-86), pages 158-162, 1986.
  49. John Lloyd. Foundations of Logic Programming. Series Symbolic Computation. Springer, second, extended edition, 1987.
  50. Nicola Leone, Gerald Pfeifer, Wolfgang Faber, and et.al. Dlv, 2010. http://www.dlvsystem.com/dlvsystem/index.php/DLV.
  51. John Lloyd and R. Topor. A basis for deductive database systems II. Journal of Logic Programming, 3(1):55-67, 1986.
  52. Vladimir Lifschitz and Hudson Turner. Splitting a logic program. In Principles of Knowledge Representation, pages 23-37. MIT Press, 1994.
  53. Jean Méhat and Tristan Cazenave. Combining uct and nested monte carlo search for single-player general game playing. IEEE Transactions on Computational Intelligence and AI in Games, 2(4):271-277, 2010.
  54. Jean Méhat and Tristan Cazenave. A parallel general game player. KI, 25(1):43-47, 2011.
  55. Drew Mcdermott. The 1998 ai planning systems competition. AI Magazine, 21:35-55, 2000.
  56. Robert Morris, editor. Deep Blue Versus Kasparov: The Signifi- cance for Artificial Intelligence. AAAI Press, 1997.
  57. Maximilian Möller, Marius Schneider, Martin Wegner, and Torsten Schaub. Centurio, a general game player: Parallel, java-and asp-based. KI, 25(1):17-24, 2011.
  58. Daniel Michulke and Michael Thielscher. Neural networks for state evaluation in general game playing. In ECML PKDD '09: Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, pages 95-110, Berlin, Heidel- berg, 2009. Springer-Verlag.
  59. John F. Nash. Equilibrium points in n-person games. In Proceed- ings of the National Academy of Sciences of the United States of America, 1950.
  60. Ilkka Niemelä, Patrik Simons, and Timo Soininen. Stable model semantics of weight constraint rules. In Proceedings of the 5th International Conference on Logic Programming and Nonmonotonic Reasoning (LPNMR'99), volume 1730 of Lecture, pages 317-331. Springer-Verlag. LNAI, 1999.
  61. University of Potsdam. Potassco, the potsdam answer set solving collection, 2010. http://potassco.sourceforge.net/.
  62. Barney Pell. Metagame in symmetric chess-like games. Heuristic Programming in Artificial Intelligence 3 -The Third Computer Olympiad, 1992.
  63. Barney Pell. Strategy generation and evaluation for meta-game playing. PhD thesis, University of Cambridge, 1993.
  64. Barney Pell. A strategic metagame player for general chess-like games. Computational Intelligence, 12:177-198, 1996.
  65. Jacques Pitrat. Realization of a general game-playing program. In IFIP Congress, pages 1570-1574, 1968.
  66. Jean-Francois Puget. Automatic detection of variable and value symmetries. In Peter van Beek, editor, CP, volume 3709 of Lecture Notes in Computer Science, pages 475-489. Springer, 2005.
  67. Alexander Reinefeld. Spielbaum-Suchverfahren, volume 200 of Informatik-Fachberichte. Springer, 1989.
  68. S. Russel and P. Norvig. Artificial Intelligence. 1995.
  69. Christian Rüdiger. Use of existing planners to solve single-player games. Großer Beleg, TU-Dresden, 2009.
  70. Ji Ruan, Wiebe van der Hoek, and Michael Wooldridge. Verification of games in the game description language. Journal of Logic and Computation, 19:1127-1156, 2009.
  71. SBB + 07] Jonathan Schaeffer, Neil Burch, Yngvi Björnsson, Akihiro Kishi- moto, Martin Muller, Robert Lake, Paul Lu, and Steve Sutphen. Checkers is solved. Science, pages 1518-1522, July 2007.
  72. J. Schaeffer. The history heuristic and alpha-beta search enhance- ments in practice. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(11), 1989.
  73. Stephan Schiffel. Symmetry detection in general game playing. In Yngvi Björnsson, Peter Stone, and Michael Thielscher, editors, Proceedings of the IJCAI-09 Workshop on General Game Playing (GIGA'09), pages 67-74, Pasadena, California, USA, July 2009.
  74. Stephan Schiffel. Symmetry detection in general game playing. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 980-985, Atlanta, July 2010. AAAI Press.
  75. Claude Shannon. Programming a computer for playing chess. Philosophical Magazine 7, 41(314):256-275, 1950.
  76. Patrik Simons. Smodels, 2008. http://www.tcs.hut.fi/Software/smodels/.
  77. Nathan R. Sturtevant and Richard E. Korf. On pruning techniques for multi-player games. In Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence, pages 201-207. AAAI Press, 2000.
  78. Shiven Sharma, Ziad Kobti, and Scott D. Goodwin. Knowledge generation for improving simulations in uct for general game playing. In Australian Joint Conference on Artificial Intelligence, pages 49- 55, 2008.
  79. Eric Schkufza, Nathaniel Love, and Michael R. Genesereth. Propo- sitional automata and cell automata: Representational frameworks for discrete dynamic systems. In Australasian Conference on Artificial Intelligence. Springer, 2008.
  80. Stephan Schiffel and Michael Thielscher. Automatic construction of a heuristic search function for general game playing. In Proceedings of the Workshop on Nonmonotonic Reasoning, Action and Change at IJCAI, Hyderabad, India, January 2007.
  81. Stephan Schiffel and Michael Thielscher. Fluxplayer: A successful general game player. In Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-07), pages 1191-1196, Vancouver, 2007. AAAI Press.
  82. Stephan Schiffel and Michael Thielscher. Automated theorem prov- ing for general game playing. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2009.
  83. Stephan Schiffel and Michael Thielscher. A multiagent semantics for the game description language. In J. Filipe, A. Fred, and B. Sharp, editors, International Conference on Agents and Artificial Intelligence (ICAART), Porto, 2009. Springer.
  84. Stephan Schiffel and Michael Thielscher. Reasoning about general games described in GDL-II. In Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, August 2011. AAAI Press.
  85. J. Tromp and G. Farnebäck. Combinatorics of go. In Proceedings of 5th International Conference on Computer and Games, Torino, Italy, May 2006.
  86. Michael Thielscher. Answer set programming for single-player games in general game playing. In P. Hill and D. Warren, editors, Proceedings of the International Conference on Logic Programming (ICLP), volume 5649 of LNCS, pages 327-341, Pasadena, July 2009. Springer.
  87. Michael Thielscher. A general game description language for incom- plete information games. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 994-999, Atlanta, July 2010. AAAI Press.
  88. Michael Thielscher and Sebastian Voigt. A temporal proof system for general game playing. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1000-1005, Atlanta, July 2010. AAAI Press.
  89. Paul E. Utgoff and Doina Precup. Constructive function approxi- mation. In Huan Huan Liu and Hiroshi Motoda, editors, Feature extraction, construction, and selection: A data-mining perspective, pages 219-235. Kluwer, 1998.
  90. A. van Gelder. The alternating fixpoint of logic programs with negation. In Proceedings of the 8th Symposium on Principles of Database Systems, pages 1-10. ACM SIGACT-SIGMOD, 1989.
  91. Dengji Zhao. Decomposition of multi-player games. Master's thesis, TU-Dresden, 2009.
  92. Albert L. Zobrist. A new hashing method with application for game playing. Technical Report 88, University of Wisconsin, April 1970.
  93. Dengji Zhao, Stephan Schiffel, and Michael Thielscher. Decom- position of multi-player games. In A. Nicholson and X. Li, editors, Proceedings of the Australasian Joint Conference on Artifi- cial Intelligence, volume 5866 of LNCS, pages 475-484, Melbourne, December 2009. Springer.

Related papers

Learning and knowledge generation in general games
Ziad Kobti

2008

General Game Playing (GGP) aims at developing game playing agents that are able to play a variety of games and in the absence of game specific knowledge, become proficient players. Most GGP players have used standard tree-search techniques enhanced by automatic heuristic learning. In this paper we explore knowledge representation and learning in GGP using Reinforcement Learning and Ant Colony Algorithms. Knowledge is created by simulating random games. We test the quality of the knowledge by comparing the performance of players using the knowledge in a variety of games. The ideas presented in this paper provide the potential for a framework for learning and knowledge representation, given the total absence of any prior knowledge.

View PDFchevron_right
Game Playing: The Next Moves
Susan Epstein

Aaai, 1999

Computer programs now play many board games as well or better than the most expert humans. Human players, however, learn, plan, allocate resources, and integrate multiple streams of knowledge. This paper highlights recent achievements in game playing, describes some cognitively-oriented work, and poses three related challenge problems for the AI community. Game Playing as a Domain Work on games has had several traditional justifications. Given unambiguous rules, playing a game to win is a well-defined problem. A game's rules create artificial world states whose granularity is explicit. There is an initial state, a state space with clear transitions, and a set of readily describable goal states. Without intervening instrumentation, games are also noise-free. For these reasons, as well as for their ability to amuse, games have often been referred to as "toy domains." To play the most difficult games well, however, a program must contend with fundamental issues in AI: knowledge representation, search, learning, and planning. There are two principal reasons to continue to do research on games, despite Deep Blue's triumph (Hamilton and Hedberg 1997). First, human fascination with game playing is long-standing and pervasive. Anthropologists have catalogued popular games in almost every culture. Indeed, the same game, under various names, often appears on many continents (Bell 1969; Zaslavsky 1982). Games intrigue us because they address important cognitive functions. In particular, the games humans like to play are probably the ones we are good at, the ones that capitalize on our intellectual strengths and forgive our weaknesses. A program that plays many games well must simulate important cognitive skills. The second reason to continue game-playing research is that some difficult games remain to be won, games that people play very well but computers do not. These games clarify what our current approach lacks. They set challenges for us to meet, and they promise ample rewards. This paper summarizes the role of search and knowledge in game playing, the state of the art, and recent relevant data on expert human game players. It then shows how cognitive skills can enhance a game-playing program, and poses three new challenge problems for the AI community. Although rooted in game playing, these challenges could enhance performance in many domains.

View PDFchevron_right
General game playing: An overview and open problems
Ziad Kobti

2009

General Game Playing has emerged, in recent years, as a challenging testbed for Artificial Intelligence research. The premise is to build game players that are able to play any game without prior knowledge about the game. The purpose of this paper is to give an overview of the open problems in the current form of General Game Playing, along with a short survey of work already done. We also provide a discussion on possible enhancements to the current format to make learning based players more viable in the competition. The aim of this paper is to highlight some of the key issues in the area of General Game Playing and generate interest amongst the academic community.

View PDFchevron_right
Multi-game playing — A challenge for computational intelligence
Jacek Mandziuk

In this paper, we deal with the topic of multi-game playing, i.e. creating agents able to autonomously learn to play any game within some arbitrarily defined genre. We describe the motivation for research in this particular area and briefly summarize the most important undertakings. Subsequently, we present a relatively young multi-game playing platform, called the General Game Playing (GGP) and our approach to development of GGP agent followed by some experimental results.

View PDFchevron_right
The international general game playing competition
Yngvi Björnsson

Games have played a prominent role as a test bed for advancements in the field of artificial intelligence ever since its foundation over half a century ago, resulting in highly specialized world-class game-playing systems being developed for various games. The establishment of the International General Game Playing Competition in 2005, however, resulted in a renewed interest in more general problem-solving approaches to game playing. In general game playing (GGP) the goal is to create game-playing systems that autonomously learn how to play a wide variety of games skillfully, given only the descriptions of the game rules. In this paper we review the history of the competition, discuss progress made so far, and list outstanding research challenges.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved