Disentangling Exploration from Exploitation

Alessandro Lizzeri, Eran Shmaya and Leeat Yariv

No 32424, NBER Working Papers from National Bureau of Economic Research, Inc

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.

JEL-codes: C73 D81 D83 O35 (search for similar items in EconPapers)
Date: 2024-05
New Economics Papers: this item is included in nep-mic and nep-ppm
Note: EH IO LE LS ME POL
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.nber.org/papers/w32424.pdf (application/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:nbr:nberwo:32424

Ordering information: This working paper can be ordered from
http://www.nber.org/papers/w32424

Access Statistics for this paper

More papers in NBER Working Papers from National Bureau of Economic Research, Inc National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.. Contact information at EDIRC.
Bibliographic data for series maintained by ().