eprintid: 4135
rev_number: 21
eprint_status: archive
userid: 351
dir: disk0/00/00/41/35
datestamp: 2016-01-15 02:04:15
lastmod: 2021-08-27 17:14:50
status_changed: 2016-01-15 02:04:15
type: monograph
metadata_visibility: show
item_issues_count: 2
creators_name: Posch, M.
creators_id: 1643
title: Cycling with a Generalized Urn Scheme and a Learning Algorithm for 2X2 Games
ispublished: pub
internal_subjects: iis_mod
internal_subjects: iis_sys
divisions: prog_dyn
abstract: In this paper we explore a learning algorithm for 2x2 games. We assume that the players neither know the payoff matrix of their opponent nor their own and can only observe their own actions and their own payoffs. We prove that the learning process, which is modelled by a generalized urn scheme, converges to a pure strategy profile if the game has at least one strict Nash equilibrium. In case there is no strict Nash equilibrium, the learning algorithm exhibits oscillations. We derive sufficient conditions that cycling occurs in a generalized urn scheme.
date: 1994-08
date_type: published
publisher: WP-94-076
iiasapubid: WP-94-076
price: 10
creators_browse_id: 1515
full_text_status: public
monograph_type: working_paper
place_of_pub: IIASA, Laxenburg, Austria
pages: 43
coversheets_dirty: FALSE
fp7_type: info:eu-repo/semantics/book
citation:   Posch, M. <https://pure.iiasa.ac.at/view/iiasa/1515.html>  (1994).  Cycling with a Generalized Urn Scheme and a Learning Algorithm for 2X2 Games.   IIASA Working Paper. IIASA, Laxenburg, Austria: WP-94-076     
document_url: https://pure.iiasa.ac.at/id/eprint/4135/1/WP-94-076.pdf