Neurosymbolic Transformers for Multi-Agent Communication
Abstract
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication. We quantify the amount of communication as the maximum degree of the communication graph; this metric captures settings where agents have limited bandwidth. Minimizing communication is challenging due to the combinatorial nature of both the decision space and the objective; for instance, we cannot solve this problem by training neural networks using gradient descent. We propose a novel algorithm that synthesizes a control policy that combines a programmatic communication policy used to generate the communication graph with a transformer policy network used to choose actions. Our algorithm first trains the transformer policy, which implicitly generates a "soft" communication graph; then, it synthesizes a programmatic communication policy that "hardens" this graph, forming a neurosymbolic transformer. Our experiments demonstrate how our approach can synthesize policies that generate low-degree communication graphs while maintaining near-optimal performance.
Cite
@article{arxiv.2101.03238,
title = {Neurosymbolic Transformers for Multi-Agent Communication},
author = {Jeevana Priya Inala and Yichen Yang and James Paulos and Yewen Pu and Osbert Bastani and Vijay Kumar and Martin Rinard and Armando Solar-Lezama},
journal= {arXiv preprint arXiv:2101.03238},
year = {2021}
}