Knowledge-Based General Game Playing

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.

[1]  Stephan Schiffel,et al.  A Multiagent Semantics for the Game Description Language , 2009, ICAART.

[2]  Maria Fox,et al.  Symmetries in planning problems , 2003 .

[3]  Frank van Harmelen,et al.  Handbook of Knowledge Representation , 2008, Handbook of Knowledge Representation.

[4]  James E. Clune,et al.  Heuristic Evaluation Functions for General Game Playing , 2007, KI - Künstliche Intelligenz.

[5]  Keki B. Irani,et al.  An Algorithmic Solution of N-Person Games , 1986, AAAI.

[6]  G Martin,et al.  Automatic Feature Construction for General Game Playing , 2008 .

[7]  Richard E. Korf,et al.  Real-Time Heuristic Search , 1990, Artif. Intell..

[8]  Gregory John Kuhlmann,et al.  Automated domain analysis and transfer learning in general game playing , 2010 .

[9]  Scott D. Goodwin,et al.  Knowledge Generation for Improving Simulations in UCT for General Game Playing , 2008, Australasian Conference on Artificial Intelligence.

[10]  Marko Grobelnik,et al.  Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II , 2009 .

[11]  Olivier Buffet,et al.  Factored Planning Using Decomposition Trees , 2007, IJCAI.

[12]  Deep Blue Versus Kasparov: The Significance for Artificial Intelligence, Collected Papers from the 1997 AAAI Workshop , 1997, Deep Blue Versus Kasparov: The Significance for Artificial Intelligence.

[13]  Jean Méhat,et al.  A Parallel General Game Player , 2010, KI - Künstliche Intelligenz.

[14]  Michael Gelfond,et al.  Answer Sets , 2008, Handbook of Knowledge Representation.

[15]  Daniel Michulke,et al.  Neural Networks for State Evaluation in General Game Playing , 2009, ECML/PKDD.

[16]  Jean-François Puget,et al.  Automatic Detection of Variable and Value Symmetries , 2005, CP.

[17]  Maria Fox,et al.  The Detection and Exploitation of Symmetry in Planning Problems , 1999, IJCAI.

[18]  Michael Wooldridge,et al.  Verification of Games in the Game Description Language , 2009, J. Log. Comput..

[19]  Yngvi Björnsson,et al.  CadiaPlayer: Search-Control Techniques , 2011, KI - Künstliche Intelligenz.

[20]  Stephan Schiffel,et al.  Fluxplayer: A Successful General Game Player , 2007, AAAI.

[21]  Claude E. Shannon,et al.  Programming a computer for playing chess , 1950 .

[22]  Igor L. Markov,et al.  Solving difficult SAT instances in the presence of symmetry , 2002, Proceedings 2002 Design Automation Conference (IEEE Cat. No.02CH37324).

[23]  Eyal Amir,et al.  Factored planning , 2003, IJCAI 2003.

[24]  Ronen I. Brafman,et al.  Factored Planning: How, When, and When Not , 2006, AAAI.

[25]  Yngvi Björnsson,et al.  Simulation-Based Approach to General Game Playing , 2008, AAAI.

[26]  Michael Thielscher,et al.  A Temporal Proof System for General Game Playing , 2010, AAAI.

[27]  J. Nash.  Equilibrium Points in N-Person Games. , 1950, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Krysia Broda,et al.  Neural-Symbolic Learning Systems , 2002 .

[29]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[30]  Stephan Schiffel.  Symmetry Detection in General Game Playing , 2010, AAAI.

[31]  Michael Thielscher.  Answer Set Programming for Single-Player Games in General Game Playing , 2009, ICLP.

[32]  Michael Thielscher,et al.  A General Game Description Language for Incomplete Information Games , 2010, AAAI.

[33]  B. Pell.  A STRATEGIC METAGAME PLAYER FOR GENERAL CHESS‐LIKE GAMES , 1994, Comput. Intell..

[34]  Stephan Schiffel,et al.  Factoring General Games , 2009 .

[35]  John Wylie Lloyd,et al.  Foundations of Logic Programming , 1987, Symbolic Computation.

[36]  Allen Van Gelder,et al.  The Alternating Fixpoint of Logic Programs with Negation , 1993, J. Comput. Syst. Sci..

[37]  Albert L. Zobrist,et al.  A New Hashing Method with Application for Game Playing , 1990 .

[38]  Michael R. Genesereth,et al.  Propositional Automata and Cell Automata: Representational Frameworks for Discrete Dynamic Systems , 2008, Australasian Conference on Artificial Intelligence.

[39]  Maria Fox,et al.  Extending the Exploitation of Symmetries in Planning , 2002, AIPS.

[40]  Richard E. Korf,et al.  On Pruning Techniques for Multi-Player Games , 2000, AAAI/IAAI.

[41]  Drew McDermott,et al.  The 1998 AI Planning Systems Competition , 2000, AI Mag..

[42]  Jacques Pitrat,et al.  Realization of a general game-playing program , 1968, IFIP Congress.

[43]  Tricia Walker,et al.  Computer science , 1996, English for academic purposes series.

[44]  David M. Kaiser,et al.  Automatic feature extraction for autonomous general game playing agents , 2007, AAMAS '07.

[45]  Michael Buro,et al.  From Simple Features to Sophisticated Evaluation Functions , 1998, Computers and Games.

[46]  Michael R. Genesereth,et al.  General Game Playing: Overview of the AAAI Competition , 2005, AI Mag..

[47]  Marius Thomas Lindauer,et al.  Centurio, a General Game Player: Parallel, Java- and ASP-based , 2010, KI - Künstliche Intelligenz.

[48]  Doina Precup,et al.  Constructive Function Approximation , 1998 .

[49]  Tom Fawcett,et al.  KNOWLEDGE‐BASED FEATURE DISCOVERY FOR EVALUATION FUNCTIONS , 1996, Comput. Intell..

[50]  Ilkka Niemelä,et al.  Stable Model Semantics of Weight Constraint Rules , 1999, LPNMR.

[51]  Stephan Schiffel,et al.  Automatic Construction of a Heuristic Search Function for General Game Playing , 2006 .

[52]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[53]  John W. Lloyd,et al.  A Basis for Deductive Database Systems II , 1986, J. Log. Program..

[54]  David M. Kaiser,et al.  The Design and Implementation of a Successful General Game Playing Agent , 2007, FLAIRS.

[55]  Barney Pell,et al.  Strategy Generation and Evaluation for Meta-Game Playing , 2011, KI - Künstliche Intelligenz.

[56]  Paul W. Goldberg,et al.  The Complexity of Computing a Nash Equilibrium , 2009, SIAM J. Comput..

[57]  Fakultat Informatik,et al.  Use of existing planners to solve single-player games , 2009 .

[58]  Yoav Shoham,et al.  Essentials of Game Theory: A Concise Multidisciplinary Introduction , 2008, Essentials of Game Theory: A Concise Multidisciplinary Introduction.

[59]  Olivier Teytaud,et al.  Modification of UCT with Patterns in Monte-Carlo Go , 2006 .

[60]  Yngvi Björnsson,et al.  Learning Simulation Control in General Game-Playing Agents , 2010, AAAI.

[61]  David M. Kaiser,et al.  The structure of games , 2005, ACM-SE 43.

[62]  Jean Méhat,et al.  Combining UCT and Nested Monte Carlo Search for Single-Player General Game Playing , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[63]  Gerald Tesauro,et al.  Temporal difference learning and TD-Gammon , 1995, CACM.

[64]  Vladimir Lifschitz,et al.  Splitting a Logic Program , 1994, ICLP.

[65]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[66]  Torsten Schaub,et al.  Automated Theorem Proving for General Game Playing , 2012 .

[67]  Stephan Schiffel,et al.  Decomposition of Multi-player Games , 2009, Australasian Conference on Artificial Intelligence.

[68]  Mesut Kirci,et al.  A GGP Feature Learning Algorithm , 2011, KI - Künstliche Intelligenz.

[69]  Jonathan Schaeffer,et al.  Checkers Is Solved , 2007, Science.

[70]  Adrian Walker,et al.  Towards a Theory of Declarative Knowledge , 1988, Foundations of Deductive Databases and Logic Programming..

[71]  Jonathan Schaeffer,et al.  The History Heuristic and Alpha-Beta Search Enhancements in Practice , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[72]  Tom Elliott Fawcett.  Feature discovery for problem solving systems , 1993 .

[73]  Keith L. Clark,et al.  Negation as Failure , 1987, Logic and Data Bases.

[74]  Stefan Edelkamp,et al.  Gamer, a General Game Playing Agent , 2010, KI - Künstliche Intelligenz.

[75]  Peter Stone,et al.  Automatic Heuristic Construction in a Complete General Game Player , 2006, AAAI.

[76]  Jaap van den Herik,et al.  Heuristic programming in Artificial Intelligence 3: the third computer olympiad , 1992 .

[77]  John Tromp,et al.  Combinatorics of Go , 2006, Computers and Games.

[78]  Rémi Coulom,et al.  Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search , 2006, Computers and Games.

[79]  Blai Bonet,et al.  Planning as heuristic search , 2001, Artif. Intell..

[80]  Bernhard Nebel,et al.  The FF Planning System: Fast Plan Generation Through Heuristic Search , 2011, J. Artif. Intell. Res..

[81]  Peter Stone,et al.  Graph-Based Domain Mapping for Transfer Learning in General Games , 2007, ECML.

[82]  Bikramjit Banerjee,et al.  General Game Learning Using Knowledge Transfer , 2007, IJCAI.

[83]  Bikramjit Banerjee and Gregory Kuhlmann and Peter Stone.  Value Function Transfer for General Game Playing , 2006 .

[84]  Stephan Schiffel,et al.  Reasoning About General Games Described in GDL-II , 2011, AAAI.