# A Regret Minimization Approach to Multi-Agent Control

arXiv: https://arxiv.org/abs/2201.13288 · HTML: https://mlsanity.com/paper/2201.13288/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 28 Jan 2022.

## Builds on (most cited first, 16 of 16)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization](https://mlsanity.com/paper/1709.08765/) (2017)
- [V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL](https://mlsanity.com/paper/2110.14555/) (2021)
- [Online Control with Adversarial Disturbances](https://mlsanity.com/paper/1902.08721/) (2019)
- [Improper Learning for Non-Stochastic Control](https://mlsanity.com/paper/2001.09254/) (2020)
- [Adaptive Regret for Control of Time-Varying Dynamics](https://mlsanity.com/paper/2007.04393/) (2020)
- [Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking](https://mlsanity.com/paper/2102.09968/) (2021)
- [Coordinate Dual Averaging for Decentralized Online Optimization with Nonseparable Global Objectives](https://mlsanity.com/paper/1508.07933/) (2015)
- [Provable Regret Bounds for Deep Online Learning and Control](https://mlsanity.com/paper/2110.07807/) (2021)
- [Generating Adversarial Disturbances for Controller Verification](https://mlsanity.com/paper/2012.06695/) (2020)
- [Consensus+Innovations Distributed Kalman Filter with Optimized Gains](https://mlsanity.com/paper/1605.06096/) (2016)
- [Distributed Control of Linear Multi-Channel Systems](https://mlsanity.com/paper/1909.11823/) (2019)
- [Distributed Learning Model Predictive Control for Linear Systems](https://mlsanity.com/paper/2006.13406/) (2020)

## Built on by (most cited first, 4 of 4)

- [Online Nonstochastic Model-Free Reinforcement Learning](https://mlsanity.com/paper/2305.17552/) (2023)
- [On observability and optimal gain design for distributed linear filtering and prediction](https://mlsanity.com/paper/2203.03521/) (2022)
- [Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics](https://mlsanity.com/paper/2412.20523/) (2024)
- [Online Multi-Agent Control with Adversarial Disturbances](https://mlsanity.com/paper/2506.18814/) (2025)

## Abstract (arXiv)

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.