Reviews: Meta-Learning Representations for Continual Learning

However, the rationale of OML in Eqn.3 is not sufficient to support the "correlated sequences". Even though consulting with Appendix B, the rationale is weak to persuade. Do you assume that the k-step online update in Eqn.3 can give optimal loss for RLN although k is smaller than the length of each session? And, what do you mean by "finding a model initialization and learning a fixed representation such that starting from the learned representation it has xyz properties (Appendix L379-380)"? - I strongly recommend the authors to move Algorithm 1 from Appendix to the paper after polishing Section 2 & 3. * Related works Missing related works make it hard to assess the novelty and significance of the proposed method. If it is possible, please do report the controlled experiments to compare state-of-the-art.