We would like to thank the reviewers for their helpful feedback, and for their positive comments regarding the originality

We will clarify this formulation in the paper. Conjugate MDPs are an interesting framework for learning useful abstractions. Thank you for your feedback - we will improve the legibility of all figures with attention to B&W . "Ours" in Figure 2 is indeed using We are indeed using the best τ found for GAE when running with λ = 0 . We will clarify this also.