Jump to ContentJump to Main Navigation
Strategic Learning and its Limits$
Users without a subscription are not able to see the full content.

H. Peyton Young

Print publication date: 2004

Print ISBN-13: 9780199269181

Published to Oxford Scholarship Online: October 2011

DOI: 10.1093/acprof:oso/9780199269181.001.0001

Show Summary Details
Page of

PRINTED FROM OXFORD SCHOLARSHIP ONLINE (www.oxfordscholarship.com). (c) Copyright Oxford University Press, 2019. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a monograph in OSO for personal use (for details see www.oxfordscholarship.com/page/privacy-policy).date: 18 July 2019

Conditional No-Regret Learning

Conditional No-Regret Learning

Chapter:
(p.43) 4 Conditional No-Regret Learning
Source:
Strategic Learning and its Limits
Author(s):

H. Peyton Young

Publisher:
Oxford University Press
DOI:10.1093/acprof:oso/9780199269181.003.0004

This chapter shows that there exist very simple adaptive rules that converge to the set of coarse correlated equilibria in a game. One of these procedures, regret matching, is as simple computationally as the most primitive reinforcement procedures; indeed it can be interpreted as a reinforcement procedure in which the aspiration level is historical average payoff. Somewhat more sophisticated procedures — such as incremental conditional regret matching and HM conditional regret matching with inertia — converge to the set of correlated equilibria in the game. The former rule differs from standard reinforcement procedures in that behaviour depends on payoff differences among actions, rather than on payoff differences relative to a given aspiration level. The latter rule depends only on payoff differences from the payoff of the current action; however, probabilistic behaviour may change abruptly from one period to the next instead of incrementally.

Keywords:   conditional regret, regret matching, learning, payoff

Oxford Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs , and if you can't find the answer there, please contact us .