eprintid: 4243 rev_number: 7 eprint_status: archive userid: 351 dir: disk0/00/00/42/43 datestamp: 2016-01-15 02:05:03 lastmod: 2021-08-27 17:15:01 status_changed: 2016-01-15 02:05:03 type: article metadata_visibility: show item_issues_count: 2 creators_name: Kaniovski, Y.M. creators_name: Young, H.P. creators_id: AL0815 creators_id: AL1397 title: Learning dynamics in games with stochastic perturbations ispublished: pub internal_subjects: iis_mod internal_subjects: iis_met internal_subjects: iis_ecn divisions: prog_ted abstract: Consider a generalization of fictitious play in which agents′ choices are perturbed by incomplete information about what the other side has done, variability in their payoffs, and unexplained trembles. These perturbed best reply dynamics define a nonstationary Markov process on an infinite state space. It is shown, using results from stochastic approximation theory, that for 2 × 2 games it converges almost surely to a point that lies close to a stable Nash equilibrium, whether pure or mixed. This generalizes a result of Fudenherg and Kreps, who demonstrate convergence when the game has a unique mixed equilibrium. date: 1995-11 date_type: published publisher: Elsevier id_number: 10.1006/game.1995.1054 iiasapubid: XJ-95-094 iiasa_bibref: Games and Economic Behavior; 11:330-363 [1995] creators_browse_id: 2009 creators_browse_id: 2539 full_text_status: none publication: Games and Economic Behavior volume: 11 number: 2 pagerange: 330-363 refereed: TRUE issn: 0899-8256 coversheets_dirty: FALSE fp7_type: info:eu-repo/semantics/article citation: Kaniovski, Y.M. & Young, H.P. (1995). Learning dynamics in games with stochastic perturbations. Games and Economic Behavior 11 (2) 330-363. 10.1006/game.1995.1054 .