Bandit problems with Lévy processes

DOI10.1287/MOOR.1120.0564zbMATH Open1304.60048arXiv1407.7241OpenAlexW2111787450MaRDI QIDQ5169656FDOQ5169656

Authors: Asaf Cohen, Eilon Solan 

Publication date: 11 July 2014

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Abstract: Bandit problems model the trade-off between exploration and exploitation in various decision problems. We study two-armed bandit problems in continuous time, where the risky arm can have two types: High or Low; both types yield stochastic payoffs generated by a Levy process. We show that the optimal strategy is a cut-off strategy and we provide an explicit expression for the cut-off and for the optimal payoff.

Full work available at URL: https://arxiv.org/abs/1407.7241

Recommendations

• Lévy bandits: Multi-armed bandits driven by Lévy processes
• Optimal stopping problems in Lévy models with random observations
• The two-armed bandit problem with continuous time in the presence of gradual and impulsive controls
• scientific article; zbMATH DE number 503440
• On the Optimal Reward Function of the Continuous Time Multiarmed Bandit Problem

zbMATH Keywords

two-armed banditsLévy processescut-off strategies

Mathematics Subject Classification ID

Processes with independent increments; Lévy processes (60G51) Stopping times; optimal stopping problems; gambling theory (60G40)

Cited In (17)

• Undiscounted bandit games
• A bandit process with delayed responses
• Optimal learning with non-Gaussian rewards
• Title not available (Why is that?)
• Parameter estimation: the proper way to use Bayesian posterior processes with Brownian noise
• Title not available (Why is that?)
• Batched bandit problems
• Two-armed restless bandits with imperfect information: stochastic control and indexability
• Title not available (Why is that?)
• Bandits and Experts in Metric Spaces
• Common value experimentation
• Lévy bandits under Poissonian decision times
• An exact bandit model for the risk-volatility tradeoff
• A stochastic differential equation driven by Poisson random measure and its application in a duopoly market
• Lévy bandits: Multi-armed bandits driven by Lévy processes
• Optimal stopping problems in Lévy models with random observations
• A common value experimentation with multiarmed bandits

This page was built for publication: Bandit problems with Lévy processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5169656)