Learning with bounded memory in games

Daniel Monte ()

Games and Economic Behavior, 2014, vol. 87, issue C, 204-223

Abstract: We study learning with bounded memory in zero-sum repeated games with one-sided incomplete information. The uninformed player has only a fixed number of memory states available. His strategy is to choose a transition rule from state to state, and an action rule, which is a map from each memory state to the set of actions. We show that the equilibrium transition rule involves randomization only in the intermediate memory states. Such randomization, or less frequent updating, is interpreted as a way of testing the opponent, which generates inertia in the player's behavior and is the main short-run bias in information processing exhibited by the bounded memory player.

Keywords: Bounded memory; Incomplete information games; Repeated games (search for similar items in EconPapers)
JEL-codes: C72 D82 D83 (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0899825614000499
Full text for ScienceDirect subscribers only

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:eee:gamebe:v:87:y:2014:i:c:p:204-223

DOI: 10.1016/j.geb.2014.03.005

Access Statistics for this article

Games and Economic Behavior is currently edited by E. Kalai

More articles in Games and Economic Behavior from Elsevier
Bibliographic data for series maintained by Catherine Liu ().