4a5cfa9281924139db466a8a19291aff-AuthorFeedback.pdf

As discussed in the paper, (2) can be relaxed tosimilar transition/reward models. Connections to prior work: We will add a more explicit discussion about the comparison to Mann et al. (2015)13 to the paper. Wewillfurther38 clarify this point in the revision.39 We will indicate in the main paper that the proof for Theorem 1 is provided in Appendix A of the supplementary49 material.