What Planning Problems Can A Relational Neural Network Solve?

arXiv:2312.03682v2 Announce Type: replace
Abstract: Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and transformers) representing policies for …

abstract arxiv circuits cs.ai cs.lg cs.ne current form however map network networks neural network neural networks next planning policies policy relational solve state stat.ml type