Work

Bounded Regret for Finite-Armed Structured Bandits

Year: 2014

Type: preprint

Abstract: We study a new type of K-armed bandit problem where the expected return of one arm may depend on the returns of other arms. We present a new algorithm for this general class of problems and show that under certain circumstances it is possible to achieve finite expected cumulative regret. We also give problem-dependent lower bounds on the cumulative regret showing that at least in special cases the new algorithm is nearly optimal.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1411.2919

Authors: Lattimore, Tor, Munos, Remi

Institutions: University of Alberta, Institut national de recherche en sciences et technologies du numérique, Centre Inria de l'Université de Lille

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W2129301967

Cites: 18

Cited by: 80

Related to: 10