This Article Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Download to citation manager Google Scholar Articles by Fang, C. Articles by Levinthal, D.

Near-Term Liability of Exploitation: Exploration and Exploitation in Multistage Problems

Department of Management and Organization, Stern School of Business, New York University, New York, New York 10012
Department of Management, The Wharton School, University of Pennsylvania, Philadelphia, Pennsylvania 19104
cfang{at}stern.nyu.edu
levinthal{at}wharton.upenn.edu

The classic trade-off between exploration and exploitation reflects the tension between gaining new information about alternatives to improve future returns and using the information currently available to improve present returns. By considering these issues in the context of a multistage, as opposed to a repeated, problem environment, we show that exploratory behavior has value quite apart from its role in revising beliefs. We show that even if current beliefs provide an unbiased characterization of the problem environment, maximizing with respect to these beliefs may lead to an inferior expected payoff relative to other mechanisms that make less aggressive use of the organization's beliefs. Search can lead to more robust actions in multistage decision problems than maximization, a benefit quite apart from its role in the updating of beliefs.

Key Words: exploration and exploitation; maximization; multistage problems; reinforcement learning; softmax choice rule