Review for NeurIPS paper: Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward

Strengths: The novelty of the paper is to provide a scalable learning method for average reward settings with guarantee of small performance loss. The work is relevant to a number of real world applications such as social networks, communication networks, transportation networks etc. Following are the highlights of the paper - The problem formulation is clear and despite having so many variables in the proofs, the mathematical notations are wisely chosen and are unambiguous. The proofs appears to be correct and I liked the way few assumptions have been used to provide theoretical guarantees. Overall I think the paper should be accepted for publication.