Near-Optimal Regret Bounds for Thompson Sampling

DOI10.1145/3088510zbMath1426.68293arXiv1209.3353OpenAlexW2752599163MaRDI QIDQ4640295

Navin Goyal, Shipra Agrawal

Publication date: 17 May 2018

Published in: Journal of the ACM (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1209.3353

zbMATH Keywords

multi-armed bandits

Mathematics Subject Classification ID

Martingales with discrete parameter (60G42) Bayesian problems; characterization of Bayes procedures (62C10) Randomized algorithms (68W20) Optimal stopping in statistics (62L15)

Related Items (11)

Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ MNL-Bandit: A Dynamic Learning Approach to Assortment Selection ⋮ Unnamed Item ⋮ On Bayesian index policies for sequential resource allocation ⋮ Unnamed Item ⋮ Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit ⋮ Learning to Optimize via Posterior Sampling ⋮ Asymptotically optimal algorithms for budgeted multiple play bandits ⋮ Unnamed Item

This page was built for publication: Near-Optimal Regret Bounds for Thompson Sampling