Abstract
Evaluating agents in decision-making applications requires assessing their skill and predicting their behaviour. Both are well developed in Poker-like situations, but less so in more complex game and model domains. This paper addresses both tasks by using Bayesian inference in a benchmark space of reference agents. The concepts are explained and demonstrated using the game of chess but the model applies generically to any domain with quantifiable options and fallible choice. Demonstration applications address questions frequently asked by the chess community regarding the stability of the rating scale, the comparison of players of different eras and/or leagues, and controversial incidents possibly involving fraud. The last include alleged under-performance, fabrication of tournament results, and clandestine use of computer advice during competition. Beyond the model world of games, the aim is to improve fallible human performance in complex, high-value tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Elo, A.: The Rating of Chessplayers, Past and Present. Arco (1978)
Haworth, G.McC.: Reference Fallible Endgame Play. ICGA J. 26(2), 81–91 (2003)
Haworth, G.McC.: Chess Endgame News. ICGA J. 28(4), 243 (2005)
Haworth, G.McC.: Gentlemen, Stop Your Engines! ICGA J. 30(3), 150–156 (2007)
Di Fatta, G., Haworth, G.McC., Regan, K.: Skill Rating by Bayesian Inference. In: Proc. IEEE (CIDM) Symposium on Computational Intelligence and Data Mining, pp. 89–94 (2009)
Nalimov, E.V., Haworth, G.McC., Heinz, E.A.: Space-Efficient Indexing of Endgame Databases for Chess. In: van den Herik, H.J., Monien, B. (eds.) Advances in Computer Games, IKAT, Maastricht, The Netherlands, vol. 9, pp. 93–113 (2001)
Jansen, P.J.: KQKR: Awareness of a Fallible Opponent. ICCA J. 15(3), 111–131 (1992)
Donkers, H.H.L.M.: Nosce Hostem: Searching with Opponent Models. Ph.D. dissertation, Univ. of Maastricht (2003)
‘Euclid’:26 Analysis of the Chess Ending King and Queen against King and Rook. In: Freeborough, E. (ed.), Kegan Paul, Trench. Trubner & Co. (1895)
Nunn, J.: Secrets of Pawnless Endings, 2nd revised edn., pp. 49–69 (2002)
Conway, E.J.: Browne’s Triumph. Chess Voice 12(2), 10 (1979)
Larkins, J.: Queen vs Rook: A Point for Our Side. Chess Voice 12(2), 11 (1979)
Stenberg, W.: Beer in the Ear. Chess Voice 12(2), 8–10 (1979)
Kopec, D.: Man-Machine Chess: Past, Present and Future. In: Belzer, J., Kent, A., Holzman, A.G., Williams, J.G. (eds.) Encyclopedia of Computer Science and Technology, vol. 26, pp. 230–270, 241–243, tinyurl.com/8faahk
Regan, K.W.: Measuring Fidelity to a Computer Agent (2007), http://www.cse.buffalo.edu/-~regan/chess/fidelity/
Guid, M., Bratko, I.: Computer Analysis of World Chess Champions. ICGA J. 29(2), 65–73 (2006)
Regan, K.W.: (2009), http://www.cse.buffalo.edu/~regan/chess/computer/compare/Tournaments/-Toga10Crafty12Results.txt
Meyer-Kahlen, S.: The SHREDDER chess engine (2007), http://www.shredderchess.com/
Friedel, F.: Cheating in Chess. In: Advances in Computer Games, Institute for Knowledge and Agent Technology (IKAT), Maastricht, The Netherlands, vol. 9, pp. 327–346 (2001)
Huber, R., Meyer-Kahlen, S.: The UCI Protocol (2000), http://www.shredderchess.com/down-load.html
Guid, M., Pérez, A., Bratko, I.: How Trustworthy is Crafty’s Analysis of Chess Champions? ICGA J. 31(3), 131–144 (2008)
Glickman, M.E.: Parameter estimation in large dynamic paired comparison experiments. J. Royal Stats. Soc., Series C (Applied Statistics) 48(3), 377–394 (1999)
Chessbase News: D.P.Singh: Supreme Talent or Flawed Genius? (2007-01-07)
Chessbase News: D.P.Singh has survived his ‘Agni Pariksha’ (2007-03-01)
Greengard, M.: Cheating Hearts Redux. The Daily Dirt Chess Blog (2006-07-07)
TWIC: Tadeusz Gniota Memorial Tournament Report. This Week in Chess (2007-07-20)
Regan, K.W.: Player-engine choice-matching data (2009), http://www.cse.buffalo.edu/~regan/-chess/fidelity/FLM.html
Berger, J.N.: Theorie und Praxis der Endspiele, p.175 (Revised 1922) (1890)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Haworth, G., Regan, K., Di Fatta, G. (2010). Performance and Prediction: Bayesian Modelling of Fallible Choice in Chess. In: van den Herik, H.J., Spronck, P. (eds) Advances in Computer Games. ACG 2009. Lecture Notes in Computer Science, vol 6048. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12993-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-12993-3_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12992-6
Online ISBN: 978-3-642-12993-3
eBook Packages: Computer ScienceComputer Science (R0)