A Note on Information-Directed Sampling and Thompson Sampling
classification
💻 cs.LG
cs.AI
keywords
samplingthompsonalgorithmsinformation-directednotethreebanditbayesian
read the original abstract
This note introduce three Bayesian style Multi-armed bandit algorithms: Information-directed sampling, Thompson Sampling and Generalized Thompson Sampling. The goal is to give an intuitive explanation for these three algorithms and their regret bounds, and provide some derivations that are omitted in the original papers.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.