Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
- In a nutshell and between all the fluff, the only key difference between EGNN and E2G is the addition of the $$ \phi(m_i) $$ term. It takes some careful reading to realize this. I believe the authors fluffed and obscured this a bit so a lazy reviewer wouldn't reject it with the reasoning that it was only a minor incremental improvement to EGNN. However, the paper still addresses a fundemental challenge in a fairly rigorous way. I would have accepted the paper regardless.