trends.barnas.net

method · first seen 5 Oct 2026

linear bandit

A sequential decision problem where expected rewards are linear in action features, solved with confidence-based exploration.

Mentions per week

0319 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

upper confidence boundsliding-window constraintsoffline-to-online reinforcement learningadversarial linear Markov decision process