Review for NeurIPS paper: MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning

The paper proposes an approach for incorporating knowledge about symmetries or equivariances into neural network policies by providing a general purpose method for constructing network layers based on knowledge of the relevant transformations. The reviews are generally positive: Identifying effective ways of incorporating prior knowledge of this type into neural networks is an important research challenge that is of interest to the community. The proposed approach for constructing network layers seems novel, although there is some prior work that explores ways of exploiting such knowledge in particular application domains, or via alternative means such as data augmentation. An important caveat of the submission, remarked upon by all reviewers is the experimental evaluation. It is currently limited to simple scenarios with perfect symmetries which provide limited evidence of the utility of the approach in more complex / less idealized scenarios.