NeurIPS 2020

Reinforcement Learning with Feedback Graphs

Meta Review

All reviewers have positive opinions of this paper, with scores of (7, 7, 6, 6). I also agree that the paper is quite novel and intriguing. The main issue appears to be readability, particularly regarding the extremely lengthy supplemental material. Quoting from the reviewers: This is a well-written theoretical paper. Although it does not demonstrate empirically that feedback graphs work in real-life problems, the underlying theory seems sound and the formal results that are presented are certainly not trivial. It appears to be the first exploration of MDPs with side-information in the form of feedback graphs.