Work

Disentangling Exploration from Exploitation

Year: 2024

Type: preprint

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 a la Gittins. Disentanglement is particularly valuable for intermediate parameter values.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2404.19116

Authors: Lizzeri, Alessandro, Shmaya, Eran, Yariv, Leeat

Institutions: National Bureau of Economic Research, Princeton University, Stony Brook University, Center for Economic and Policy Research

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

Funder: National Science Foundation

Award: Collaborative Research: Disentangling Exploration from Exploitation

OpenAlex ID: W4396600206

Cites:

Cited by:

Related to: