0f0e13216262f4a201bec128044dd30f-AuthorFeedback.pdf

We thank all reviewers for their careful reading of our paper and their constructive feedback. Thank you for expressing your appreciation of our results and your thoughtful comments! For instance, we refer to some relevant papers from NeurIPS 2019: "Non-6 Minimization in Discrete and Continuous Average Reward MDPs" (34 pages), "Tight Regret Bounds for Reviewer #3 Thank you for your positive evaluation of our paper! " is indeed a very interesting question, but also a rather complex one. P AC-MDP algorithms also rely on the same notion of optimism as used for proving regret bounds.