Pack Light on the Move: Exploitation and Exploration in a Dynamic Environment

17 Pages Posted: 13 Sep 2013

See all articles by Marco LiCalzi

Marco LiCalzi

Dept. Management, Università Ca' Foscari Venezia

Davide Marchiori

Ca Foscari University of Venice

Date Written: April 2013

Abstract

This paper revisits a recent study by Posen and Levinthal (2012) on the exploration/exploitation tradeoff for a multi-armed bandit problem, where the reward probabilities undergo random shocks. We show that their analysis suffers two shortcomings: it assumes that learning is based on stale evidence, and it overlooks the steady state. We let the learning rule endogenously discard stale evidence, and we perform the long run analyses. The comparative study demonstrates that some of their conclusions must be qualified.

Keywords: adaptation, learning, turbulence, multi-armed bandit problem

JEL Classification: D83

Suggested Citation

LiCalzi, Marco and Marchiori, Davide, Pack Light on the Move: Exploitation and Exploration in a Dynamic Environment (April 2013). Department of Management, Università Ca' Foscari Venezia Working Paper No. 4/2013, Available at SSRN: https://ssrn.com/abstract=2324420 or http://dx.doi.org/10.2139/ssrn.2324420

Marco LiCalzi (Contact Author)

Dept. Management, Università Ca' Foscari Venezia ( email )

San Giobbe, Cannaregio 873
Venice, 30121
Italy
+39-0412346925 (Phone)
+39-0412347444 (Fax)

HOME PAGE: http://venus.unive.it/licalzi/

Davide Marchiori

Ca Foscari University of Venice ( email )

Dorsoduro 3246
Venezia, 30123
Italy

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
16
Abstract Views
410
PlumX Metrics