A Regret Minimization Approach to Multi-Agent Control

TL;DR

This paper introduces a distributed regret minimization framework for multi-agent control of dynamical systems, enabling adaptive policies that are robust to adversarial disturbances without relying on centralized precomputed solutions.

Contribution

It generalizes online convex optimization to multi-agent control, providing a reduction from regret minimization to distributed algorithms with robustness guarantees.

Findings

Distributed algorithm achieves low regret compared to optimal joint policy.

Method is robust to agent failure and adversarial perturbations.

Empirical evaluation on aircraft model demonstrates effectiveness.

Abstract

We study the problem of multi-agent control of a dynamical system with known dynamics and adversarial disturbances. Our study focuses on optimal control without centralized precomputed policies, but rather with adaptive control policies for the different agents that are only equipped with a stabilizing controller. We give a reduction from any (standard) regret minimizing control method to a distributed algorithm. The reduction guarantees that the resulting distributed algorithm has low regret relative to the optimal precomputed joint policy. Our methodology involves generalizing online convex optimization to a multi-agent setting and applying recent tools from nonstochastic control derived for a single agent. We empirically evaluate our method on a model of an overactuated aircraft. We show that the distributed method is robust to failure and to adversarial perturbations in the dynamics.