mlsanityData to 7 Oct 2026

A Regret Minimization Approach to Multi-Agent Control

arXiv 2201.13288 ↗First posted 28 Jan 2022math.OC cs.LG stat.MLcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 28 Jan 2022.

Builds on

16 of 45 references.

References · 16

  1. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  2. 2019Introduction to Online Convex Optimizationcited by 793
  3. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  4. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  5. 2017Network Topology and Communication-Computation Tradeoffs in Decentralized Optimizationcited by 119
  6. 2021V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RLcited by 111
  7. 2019Online Control with Adversarial Disturbancescited by 92
  8. 2020Improper Learning for Non-Stochastic Controlcited by 83
  9. 2020Adaptive Regret for Control of Time-Varying Dynamicscited by 38
  10. 2021Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarkingcited by 10
  11. 2015Coordinate Dual Averaging for Decentralized Online Optimization with Nonseparable Global Objectivescited by 7
  12. 2021Provable Regret Bounds for Deep Online Learning and Controlcited by 6
4 more
  1. 2020Generating Adversarial Disturbances for Controller Verificationcited by 4
  2. 2016Consensus+Innovations Distributed Kalman Filter with Optimized Gainscited by 3
  3. 2019Distributed Control of Linear Multi-Channel Systemscited by 1
  4. 2020Distributed Learning Model Predictive Control for Linear Systemscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 1.

4 papers.

  1. 2023Online Nonstochastic Model-Free Reinforcement Learningcited by 2
  2. 2022On observability and optimal gain design for distributed linear filtering and predictioncited by 1
  3. 2024Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamicscited by 1
  4. 2025Online Multi-Agent Control with Adversarial Disturbancescited by 0