Regret Minimization Under Partial Monitoring

DOI10.1287/moor.1060.0206zbMath1276.91019OpenAlexW1964631708WikidataQ59538585 ScholiaQ59538585MaRDI QIDQ5387997

Nicolò Cesa-Bianchi, Gilles Stoltz, Gábor Lugosi

Publication date: 27 May 2008

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

Full work available at URL: https://doi.org/10.1287/moor.1060.0206

zbMATH Keywords

imperfect monitoringHannan consistencyinternal regret

Mathematics Subject Classification ID

2-person games (91A05) Multistage and repeated games (91A20)

Related Items (13)

A general internal regret-free strategy ⋮ Improving multi-armed bandit algorithms in online pricing settings ⋮ Improved second-order bounds for prediction with expert advice ⋮ On robustness and dynamics in (un)balanced coalitional games ⋮ Constrained no-regret learning ⋮ The \(K\)-armed dueling bandits problem ⋮ Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments ⋮ Randomized prediction of individual sequences ⋮ Repeated Games with Incomplete Information ⋮ Robust dynamic cooperative games ⋮ Game of Thrones: Fully Distributed Learning for Multiplayer Bandits ⋮ Partial Monitoring—Classification, Regret Bounds, and Algorithms ⋮ Unnamed Item

This page was built for publication: Regret Minimization Under Partial Monitoring