Disentangling Exploration from Exploitation

Alessandro Lizzeri, Eran Shmaya and Leeat Yariv
Additional contact information
Eran Shmaya: State University of New York at Stony Brook
Leeat Yariv: Princeton University, CEPR, and NBER

Working Papers from Princeton University, Department of Economics, Center for Economic Policy Studies.

Abstract: Starting from Robbins (1952), the literature on experimentation via multi-armed bandits has wed exploration and exploitation. Nonetheless, in many applications, agents’ exploration and exploitation need not be intertwined: a policymaker may assess new policies different than the status quo; an investor may evaluate projects outside her portfolio. We characterize the optimal experimentation policy when exploration and exploitation are disentangled in the case of Poisson bandits, allowing for general news structures. The optimal policy features complete learning asymptotically, exhibits lots of persistence, but cannot be identified by an index à la Gittins. Disentanglement is particularly valuable for intermediate parameter values.

Keywords: Exploration and Exploitation; Poisson Bandits (search for similar items in EconPapers)
JEL-codes: C73 D81 D83 O35 (search for similar items in EconPapers)
Date: 2024-04
New Economics Papers: this item is included in nep-mic and nep-ppm
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://gceps.princeton.edu/wp-content/uploads/202 ... tionExploitation.pdf

Related works:
Working Paper: Disentangling Exploration from Exploitation (2024)
Working Paper: Disentangling Exploration from Exploitation (2024)
Working Paper: Disentangling Exploration from Exploitation (2024)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pri:cepsud:334

Access Statistics for this paper

More papers in Working Papers from Princeton University, Department of Economics, Center for Economic Policy Studies. Contact information at EDIRC.
Bibliographic data for series maintained by Bobray Bordelon ().