Online Multi-Agent Control with Adversarial Disturbances

• URL: http://arxiv.org/abs/2506.18814v2
• Date: Fri, 26 Sep 2025 09:12:28 GMT
• Title: Online Multi-Agent Control with Adversarial Disturbances
• Authors: Anas Barakat, John Lazarsfeld, Georgios Piliouras, Antonios Varvitsiotis,
• Abstract summary: We study online control in multi-agent linear dynamical systems subject to adversarial disturbances.<n>Our results take a first step in bridging online control with online learning in games, establishing robust individual collective performance guarantees.
• Score: 26.881668342043373
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online multi-agent control problems, where many agents pursue competing and time-varying objectives, are widespread in domains such as autonomous robotics, economics, and energy systems. In these settings, robustness to adversarial disturbances is critical. In this paper, we study online control in multi-agent linear dynamical systems subject to such disturbances. In contrast to most prior work in multi-agent control, which typically assumes noiseless or stochastically perturbed dynamics, we consider an online setting where disturbances can be adversarial, and where each agent seeks to minimize its own sequence of convex losses. Under two feedback models, we analyze online gradient-based controllers with local policy updates. We prove per-agent regret bounds that are sublinear and near-optimal in the time horizon and that highlight different scalings with the number of agents. When agents' objectives are aligned, we further show that the multi-agent control problem induces a time-varying potential game for which we derive equilibrium tracking guarantees. Together, our results take a first step in bridging online control with online learning in games, establishing robust individual and collective performance guarantees in dynamic continuous-state environments.

Related papers

• Diffusion Forcing for Multi-Agent Interaction Sequence Modeling [52.769202433667125]
  MAGNet is a unified autoregressive diffusion framework for multi-agent motion generation.<n>It supports a wide range of interaction tasks through flexible conditioning and sampling.<n>It captures both tightly synchronized activities and loosely structured social interactions.
  arXiv  Detail & Related papers  (2025-12-19T18:59:02Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• VariAntNet: Learning Decentralized Control of Multi-Agent Systems [2.5950969608246797]
  A simple multi-agent system can be effectively utilized in disaster response applications, such as firefighting.<n>These simple robotic agents, also known as Ant Robots, are defined as anonymous agents that possess limited sensing capabilities, lack a shared coordinate system, and do not communicate explicitly with one another.<n>We propose VariAntNet, a deep learning-based decentralized control model designed to facilitate agent swarming and collaborative task execution.
  arXiv  Detail & Related papers  (2025-09-02T12:48:15Z)
• Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems [0.0]
  This report addresses the early stages of risk identification and analysis for multi-agent AI systems.<n>We examine six critical failure modes: cascading reliability failures, inter-agent communication failures, monoculture collapse, conformity bias, deficient theory of mind, and mixed motive dynamics.
  arXiv  Detail & Related papers  (2025-08-06T06:06:57Z)
• PeerGuard: Defending Multi-Agent Systems Against Backdoor Attacks Through Mutual Reasoning [8.191214701984162]
  Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks.<n>Despite their growing importance, safety in multi-agent systems remains largely underexplored.<n>This work investigates backdoor vulnerabilities in multi-agent systems and proposes a defense mechanism based on agent interactions.
  arXiv  Detail & Related papers  (2025-05-16T19:08:29Z)
• Free Agent in Agent-Based Mixture-of-Experts Generative AI Framework [0.0]
  Reinforcement Learning Free Agent (RLFA) algorithm introduces a reward-based mechanism to detect and remove agents exhibiting persistent underperformance.<n>A primary use case is fraud detection, where RLFA promptly swaps out an agent whose detection accuracy dips below a preset threshold.<n>This dynamic, free-agency cycle ensures sustained accuracy, quicker adaptation to emerging threats, and minimal disruption to ongoing operations.
  arXiv  Detail & Related papers  (2025-01-29T13:00:22Z)
• Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments [3.0284592792243794]
  Bottom Up Network (BUN) treats the collective of multi-agents as a unified entity. Our empirical evaluations across a variety of cooperative multi-agent scenarios, including tasks such as cooperative navigation and traffic control, consistently demonstrate BUN's superiority over baseline methods with substantially reduced computational costs.
  arXiv  Detail & Related papers  (2024-10-03T14:25:02Z)
• EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms [55.77492625524141]
  EvoAgent is a generic method to automatically extend specialized agents to multi-agent systems.<n>We show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents.
  arXiv  Detail & Related papers  (2024-06-20T11:49:23Z)
• Collision Avoidance Verification of Multiagent Systems with Learned Policies [9.550601011551024]
  This paper presents a backward reachability-based approach for verifying the collision avoidance properties of Multi-Agent Feedback Loops (MA-NFLs) We account for many uncertainties, making it well aligned with real-world scenarios. We demonstrate the proposed algorithm can verify collision-free properties of a MA-NFL with agents trained to imitate a collision avoidance algorithm.
  arXiv  Detail & Related papers  (2024-03-05T20:36:26Z)
• Mix-ME: Quality-Diversity for Multi-Agent Learning [11.130914000431353]
  We introduce Mix-ME, a novel multi-agent variant of the popular MAP-Elites algorithm. We evaluate the proposed methods on a variety of partially observable continuous control tasks.
  arXiv  Detail & Related papers  (2023-11-03T10:36:54Z)
• Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning [54.788422270960496]
  We propose a novel multi-agent offline RL algorithm, named CounterFactual Conservative Q-Learning (CFCQL) CFCQL calculates conservative regularization for each agent separately in a counterfactual way and then linearly combines them to realize an overall conservative value estimation. We prove that it still enjoys the underestimation property and the performance guarantee as those single agent conservative methods do, but the induced regularization and safe policy improvement bound are independent of the agent number.
  arXiv  Detail & Related papers  (2023-09-22T08:10:25Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  MADiff is a diffusion-based multi-agent learning framework.<n>It works as both a decentralized policy and a centralized controller.<n>Our experiments demonstrate that MADiff outperforms baseline algorithms across various multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)
• On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring [105.13668993076801]
  A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees. We study this question in a general framework for interactive decision making with multiple agents. We show that characterizing the statistical complexity for multi-agent decision making is equivalent to characterizing the statistical complexity of single-agent decision making.
  arXiv  Detail & Related papers  (2023-05-01T06:46:22Z)
• A Policy Iteration Approach for Flock Motion Control [5.419608513284392]
  The overall control process guides the agents while monitoring the flock-cohesiveness and localization. An online model-free policy iteration mechanism is developed here to guide a flock of agents to follow an independent command generator. The simulation results of the policy iteration mechanism revealed fast learning and convergence behaviors with less computational effort.
  arXiv  Detail & Related papers  (2023-03-17T15:04:57Z)
• Learning From Good Trajectories in Offline Multi-Agent Reinforcement Learning [98.07495732562654]
  offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets. One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team. We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
  arXiv  Detail & Related papers  (2022-11-28T18:11:26Z)
• Isolating and Leveraging Controllable and Noncontrollable Visual Dynamics in World Models [65.97707691164558]
  We present Iso-Dream, which improves the Dream-to-Control framework in two aspects. First, by optimizing inverse dynamics, we encourage world model to learn controllable and noncontrollable sources. Second, we optimize the behavior of the agent on the decoupled latent imaginations of the world model.
  arXiv  Detail & Related papers  (2022-05-27T08:07:39Z)
• A Regret Minimization Approach to Multi-Agent Control [24.20403443262127]
  We study the problem of multi-agent control of a dynamical system with known dynamics and adversarial disturbances. We give a reduction from any (standard) regret minimizing control method to a distributed algorithm. We show that the distributed method is robust to failure and to adversarial perturbations in the dynamics.
  arXiv  Detail & Related papers  (2022-01-28T14:57:59Z)
• Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification [74.10976684469435]
  offline reinforcement learning (RL) algorithms can be transferred to multi-agent settings directly. We propose a simple yet effective method, Offline Multi-Agent RL with Actor Rectification (OMAR), to tackle this critical challenge. OMAR significantly outperforms strong baselines with state-of-the-art performance in multi-agent continuous control benchmarks.
  arXiv  Detail & Related papers  (2021-11-22T13:27:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.