This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Learning to play games in extensive form by valuation

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Philippe Jehiel
Dov Samet

Additional information is available for the following registered author(s):

Abstract

A valuation for a board game is an assignment of numeric values to different states of the board. The valuation reflects the desirability of the states for the player. It can be used by a player to decide on her next move during the play. We assume a myopic player, who chooses a move with the highest valuation. Valuations can also be revised, and hopefully improved, after each play of the game. Here, a very simple valuation revision is considered, in which the states of the board visited in a play are assigned the payoff obtained in the play. We show that by adopting such a learning process a player who has a winning strategy in a win-lose game can almost surely guarantee a win in a repeated game. When a player has more than two payoffs, a more elaborate learning procedure is required. We consider one that associates with each state the average payoff in the rounds in which this node was reached. When all players adopt this learning procedure, with some perturbations, then, with probability 1, strategies that are close to subgame perfect equilibrium are played after some time. A single player who adopts this procedure can guarantee only her individually rational payoff.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help file. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://129.3.20.41/eps/game/papers/0012/0012001.pdf
File Format: application/pdf
File Function:
Download Restriction: no

Publisher Info
Paper provided by EconWPA in its series Game Theory and Information with number 0012001.

Download reference. The following formats are available: HTML, plain text, BibTeX, RIS (EndNote), ReDIF
Length: 18 pages
Date of creation: 01 Jan 2001
Date of revision:
Handle: RePEc:wpa:wuwpga:0012001

Note: Type of Document - ; pages: 18
Contact details of provider:
Web page: http://129.3.20.41

For technical questions regarding this item, or to correct its listing, contact: (EconWPA).

Related research
Keywords: reinforcement learning

Other versions of this item:

Find related papers by JEL classification:
C7 - Mathematical and Quantitative Methods - - Game Theory and Bargaining Theory
D8 - Microeconomics - - Information, Knowledge, and Uncertainty

This paper has been announced in the following NEP Reports:

References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
  1. Camerer, Colin & Ho, Teck-Hua, 1997. "Experience-Weighted Attraction Learning in Games: A Unifying Approach," Working Papers 1003, California Institute of Technology, Division of the Humanities and Social Sciences. [Downloadable!]
  2. Erev, Ido & Roth, Alvin E, 1998. "Predicting How People Play Games: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria," American Economic Review, American Economic Association, vol. 88(4), pages 848-81, September. [Downloadable!] (restricted)
  3. Sarin, Rajiv & Vahid, Farshid, 1999. "Payoff Assessments without Probabilities: A Simple Dynamic Model of Choice," Games and Economic Behavior, Elsevier, vol. 28(2), pages 294-309, August. [Downloadable!] (restricted)
  4. Gilboa, Itzhak & Schmeidler, David, 1995. "Case-Based Decision Theory," The Quarterly Journal of Economics, MIT Press, vol. 110(3), pages 605-39, August. [Downloadable!] (restricted)
    Other versions:
Full references

Cited by:
(explanations, Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.)

  1. Philippe Jehiel & Dov Samet, 2006. "Valuation Equilibria," Levine's Bibliography 784828000000000111, UCLA Department of Economics. [Downloadable!]
    Other versions:
  2. Francesco Squintani, 2004. "Backward Induction and Model Deterioration," Advances in Theoretical Economics, Berkeley Electronic Press, vol. 4(1), pages 1157-1157. [Downloadable!] (restricted)
    Other versions:
  3. Drew Fudenberg & David K. Levine, 2006. "Superstition and Rational Learning," American Economic Review, American Economic Association, vol. 96(3), pages 630-651, June.
    Other versions:
  4. Drew Fudenberg & David K Levine, 2006. "An Economists Perspective on Multi-Agent Learning," Levine's Working Paper Archive 784828000000000683, UCLA Department of Economics. [Downloadable!]
  5. Yoav Shoham & Rob Powers & Trond Grenager, 2006. "If multi-agent learning is the answer, what is the question?," Levine's Working Paper Archive 122247000000001156, UCLA Department of Economics. [Downloadable!]
Statistics
Access and download statistics

Did you know? All full texts are decentralized with the publishers, none reside on this server, thus making it possible to offer this service for free to all parties.

This page was last updated on 2008-8-8.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.