Generalized reinforcement learning in perfect-information games

Maxwell Pak and Bing Xu ()
Additional contact information
Bing Xu: Southwestern University of Finance and Economics

International Journal of Game Theory, 2016, vol. 45, issue 4, No 10, 985-1011

Abstract: Abstract This paper studies reinforcement learning in which players base their action choice on valuations they have for the actions. We identify two general conditions on valuation updating rules that together guarantee that the probability of playing a subgame perfect Nash equilibrium (SPNE) converges to one in games where no player is indifferent between two outcomes without every other player being also indifferent. The same conditions guarantee that the fraction of times a SPNE is played converges to one almost surely. We also show that for additively separable valuations, in which valuations are the sum of empirical and error terms, the conditions guaranteeing convergence can be made more intuitive. In addition, we give four examples of valuations that satisfy our conditions. These examples represent different degrees of sophistication in learning behavior and include well-known examples of reinforcement learning.

Keywords: Reinforcement learning; Extensive-form games (search for similar items in EconPapers)
JEL-codes: D83 (search for similar items in EconPapers)
Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s00182-015-0499-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jogath:v:45:y:2016:i:4:d:10.1007_s00182-015-0499-1

Ordering information: This journal article can be ordered from
http://www.springer. ... eory/journal/182/PS2

DOI: 10.1007/s00182-015-0499-1

Access Statistics for this article

International Journal of Game Theory is currently edited by Shmuel Zamir, Vijay Krishna and Bernhard von Stengel

More articles in International Journal of Game Theory from Springer, Game Theory Society
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().