When Should Agents Coordinate in Differentiable Sequential Decision Problems?

TL;DR

This paper investigates when multi-agent systems should coordinate in differentiable motion-planning tasks, proposing algorithms that analyze second-order properties to determine optimal coordination timing, balancing communication costs and team performance.

Contribution

It introduces a framework for modeling and analyzing the spectrum of coordination strategies in differentiable motion-planning problems, with algorithms to decide optimal coordination moments.

Findings

Coordination decisions can be derived from second-order objective analysis.

Algorithms effectively identify when agents should coordinate.

Coordination timing improves team performance while reducing communication costs.

Abstract

Multi-robot teams must coordinate to operate effectively. When a team operates in an uncoordinated manner, and agents choose actions that are only individually optimal, the team's outcome can suffer. However, in many domains, coordination requires costly communication. We explore the value of coordination in a broad class of differentiable motion-planning problems. In particular, we model coordinated behavior as a spectrum: at one extreme, agents jointly optimize a common team objective, and at the other, agents make unilaterally optimal decisions given their individual decision variables, i.e., they operate at Nash equilibria. We then demonstrate that reasoning about coordination in differentiable motion-planning problems reduces to reasoning about the second-order properties of agents' objectives, and we provide algorithms that use this second-order reasoning to determine at which times a team of agents should coordinate.