Game-theoretic learning using the imprecise Dirichlet model

Erik Quaeghebeur, Gert de Cooman

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

We discuss two approaches for choosing a strategy in a two-player game. We suppose that the game is played a large number of rounds, which allows the players to use observations of past play to guide them in choosing a strategy. Central in these approaches is the way the opponent's next strategy is assessed; both a precise and an imprecise Dirichlet model are used. The observations of the opponent's past strategies can then be used to update the model and obtain new assessments. To some extent, the imprecise probability approach allows us to avoid making arbitrary initial assessments. To be able to choose a strategy, the assessment of the opponent's strategy is combined with rules for selecting an optimal response to it: a so-called best response or a maximin strategy. Together with the updating procedure, this allows us to choose strategies for all the rounds of the game. The resulting playing sequence can then be analysed to investigate if the strategy choices can converge to equilibria.
Original languageEnglish
Title of host publicationProceedings of the third international symposium on imprecise probabilities and their applications
EditorsJean-Marc Bernard, Teddy Seidenfeld, Marco Zaffalon
Place of PublicationCanada
PublisherCarleton Scientific, Canada
Pages452-466
ISBN (Print)9781894145176
Publication statusPublished - 2003
Externally publishedYes
Event3rd International symposium on Imprecise Probabilities and Their Applications - University of Lugano, Lugano, Switzerland
Duration: 14 Jul 200317 Jul 2003
http://www.sipta.org/isipta03/

Publication series

NameProceedings in Informatics
PublisherCarleton Scientific
Volume18

Conference

Conference3rd International symposium on Imprecise Probabilities and Their Applications
Abbreviated titleISIPTA '03
CountrySwitzerland
CityLugano
Period14/07/0317/07/03
Internet address

Cite this

Quaeghebeur, E., & de Cooman, G. (2003). Game-theoretic learning using the imprecise Dirichlet model. In J-M. Bernard, T. Seidenfeld, & M. Zaffalon (Eds.), Proceedings of the third international symposium on imprecise probabilities and their applications (pp. 452-466). (Proceedings in Informatics; Vol. 18). Carleton Scientific, Canada. http://www.sipta.org/isipta03/proc/019.html