NeurIPS 2020

Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss

Meta Review

I want to thank the authors for preparing the detailed rebuttal. This paper was discussed among all the reviewers during the post-rebuttal discussion phase. Overall, the reviewers are excited about this work on solving constrained MDP problems and have a positive assessment of the paper. All the reviewers acknowledged the theoretical contributions, especially in a challenging setting with unknown dynamics and non-stationary loss function. There was a clear consensus that the paper should be accepted. The reviewers have provided detailed feedback in their reviews, and we hope that the authors can incorporate this feedback when preparing the final version of the paper.