Ghent University Academic Bibliography

Advanced

Game-theoretic learning using the imprecise Dirichlet model

Erik Quaeghebeur and Gert De Cooman UGent (2003) Proceedings in Informatics. 18. p.452-466
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.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
imprecise Dirichlet model, game theory, fictitious play, learning, equilibria
in
Proceedings in Informatics
editor
Jean-Marc Bernard, Teddy Seidenfeld and Marco Zaffalon
volume
18
issue title
Proceedings of the third international symposium on imprecise probabilities and their applications
pages
452 - 466
publisher
Carleton Scientific
conference name
3rd International symposium on Imprecise Probabilities and Their Applications (ISIPTA '03)
conference location
Lugano, Switzerland
conference start
2003-07-14
conference end
2003-7-17
ISBN
9781894145176
language
English
UGent publication?
yes
classification
C1
copyright statement
I have transferred the copyright for this publication to the publisher
id
213482
handle
http://hdl.handle.net/1854/LU-213482
date created
2004-04-29 13:35:00
date last changed
2016-12-19 15:35:37
@inproceedings{213482,
  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.},
  author       = {Quaeghebeur, Erik and De Cooman, Gert},
  booktitle    = {Proceedings in Informatics},
  editor       = {Bernard, Jean-Marc and Seidenfeld, Teddy and Zaffalon, Marco},
  isbn         = {9781894145176},
  keyword      = {imprecise Dirichlet model,game theory,fictitious play,learning,equilibria},
  language     = {eng},
  location     = {Lugano, Switzerland},
  pages        = {452--466},
  publisher    = {Carleton Scientific},
  title        = {Game-theoretic learning using the imprecise Dirichlet model},
  volume       = {18},
  year         = {2003},
}

Chicago
Quaeghebeur, Erik, and Gert De Cooman. 2003. “Game-theoretic Learning Using the Imprecise Dirichlet Model.” In Proceedings in Informatics, ed. Jean-Marc Bernard, Teddy Seidenfeld, and Marco Zaffalon, 18:452–466. Carleton Scientific.
APA
Quaeghebeur, E., & De Cooman, G. (2003). Game-theoretic learning using the imprecise Dirichlet model. In J.-M. Bernard, T. Seidenfeld, & M. Zaffalon (Eds.), Proceedings in Informatics (Vol. 18, pp. 452–466). Presented at the 3rd International symposium on Imprecise Probabilities and Their Applications (ISIPTA  ’03), Carleton Scientific.
Vancouver
1.
Quaeghebeur E, De Cooman G. Game-theoretic learning using the imprecise Dirichlet model. In: Bernard J-M, Seidenfeld T, Zaffalon M, editors. Proceedings in Informatics. Carleton Scientific; 2003. p. 452–66.
MLA
Quaeghebeur, Erik, and Gert De Cooman. “Game-theoretic Learning Using the Imprecise Dirichlet Model.” Proceedings in Informatics. Ed. Jean-Marc Bernard, Teddy Seidenfeld, & Marco Zaffalon. Vol. 18. Carleton Scientific, 2003. 452–466. Print.