Early-Signal Detector

task · first seen 4 Oct 2026

multi-armed bandit

Also: MAB, MMAB, bandits, bandit problem, bandit feedback, bandit algorithm, stochastic bandits

A sequential decision problem where an agent repeatedly chooses among arms with unknown rewards to maximize cumulative reward.

Mentions per week

0819 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

Thompson samplingthumbnail selectionNash social welfareadversarial attacks on banditsempirical likelihoodLLM routinggame-theoretic evaluationgreedy approximation algorithmspeculative decodingself-speculative decoding