We thank the reviewers for their thoughtful feedback, and note the apparent consensus that our contribution, Sibling

Rivalry (SR), is interesting and novel. We will fix all writing issues and revise the title and notation. Such "local optima" are, e.g., low-entropy We will add the results to the Appendix. Note that local optima hinder learning even with "good" Sample complexity We will plot results in terms of sampled timesteps rather than episodes. F ormal analysis Our work contributes an extensive empirical validation of SR, we leave formal analysis for future work.