analysis and our analysis of FRANCIS remains unchanged, we wish to note that in our own internal re-review we

We thank the reviewers for their thoughtful reviews; below we address their main concerns. This allows us to express the misspecification error (e.g., eqn 37 in appendix) directly in every (null 1) Note that the results from Chi et al. We consider this work as a first step in this direction. Is a good representation sufficient for sample efficient reinforcement learning?