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

Marco LiCalzi, Davide Marchiori

Research output: Chapter in Book/Report/Conference proceedingBook chapterResearchpeer-review

Abstract

This paper revisits a recent study by Posen and Levinthal (Manag Sci 58:587–601, 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.
Original languageEnglish
Title of host publicationArtificial Economics and Self Organization : Agent-Based Approaches to Economics and Social Systems
EditorsStephan Leitner, Friederike Wall
PublisherSpringer
Publication date2014
Pages205-216
ISBN (Print)9783319009117
ISBN (Electronic)9783319009124
DOIs
Publication statusPublished - 2014
SeriesLecture Notes in Economics and Mathematical Systems
Volume669
ISSN0075-8442

Fingerprint

Dive into the research topics of 'Pack Light on the Move: Exploitation and Exploration in a Dynamic Environment'. Together they form a unique fingerprint.

Cite this