The Multi-Armed Bandit Problem and Thompson Sampling
About this video
Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceExplains the multi-armed bandit problem and Thompson sampling, a key exploration-exploitation algorithm in online learning. A 37-minute lecture teaching a fundamental decision-making framework.
A 37-minute video from Microsoft Research: “The Multi-Armed Bandit Problem and Thompson Sampling”.
Video by Microsoft Research, played through YouTube's embedded player.