as the reviewers were happy with the motivation and practicality of our work. believe that our novelty is in proposing Thompson sampling latent bandit algorithms using offline-learned graphical

We would like to thank the reviewers for their insightful reviews. The primary weakness that several reviewers brought up was that the methods and analysis were straightforward. Reviewer #1 "algorithm... is not designed keeping short horizons in mind": Our algorithms quickly personalize by Reviewer #2 "suffers an exploration-exploitation tradeoff": You are correct in noting that our algorithm depends on "unified analyses cannot cover instance-dependent bounds": We derive Bayes regret bounds, which contain an expectation Reviewer #3 Thank you for your detailed corrections! We will update the paper with your clarifications. "the available epsilon-bounds are wildly pessimistic": You are correct in noting that our regret bounds require that the Updating our regret bounds to reflect this is a future line of work.