Bandit algorithms based on Thompson sampling for bounded reward distributions

MaRDI QIDQ7025113zbMATH OpenFDO

Authors Charles Riou, Junya Honda

Publication date 19 February 2025

Full work available at URL https://proceedings.mlr.press/v117/riou20a.html

zbMATH Keywords

multi-armed bandit problemonline optimizationrandomized algorithmreinforcement learningThompson sampling

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20)

Cites work

• Asymptotically efficient adaptive allocation rules
• Finite-time analysis of the multiarmed bandit problem
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
• Optimal adaptive policies for sequential allocation problems
• Thompson sampling: an asymptotically optimal finite-time analysis

Cited in

(1)

• Follow-the-perturbed-leader achieves best-of-both-worlds for bandit problems

This page was built for publication: Bandit algorithms based on Thompson sampling for bounded reward distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7025113)