Self-Configurable Mesh-Networks for Scalable Distributed Submodular Bandit Optimization

2026-02-22

AI Summary

This work addresses the challenge of scalable distributed submodular optimization and multi-agent coordination under realistic communication constraints—limited bandwidth, data rates, and connectivity. The authors propose a coordination mechanism that relies solely on single-hop communication, where each message contains only local action information. They introduce a Value-of-Coordination (VoC) metric to dynamically optimize communication neighborhoods, enabling adaptation to arbitrary network topologies, including disconnected graphs. Notably, this approach provides, for the first time, a strictly positive suboptimality bound at any time step, achieving joint optimization of communication and decision-making. Experimental results demonstrate that the method converges faster than existing submodular coordination baselines and even outperforms approaches that leverage prior environmental knowledge.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

We study how to scale distributed bandit submodular coordination under realistic communication constraints in bandwidth, data rate, and connectivity. We are motivated by multi-agent tasks of active situational awareness in unknown, partially-observable, and resource-limited environments, where the agents must coordinate through agent-to-agent communication. Our approach enables scalability by (i) limiting information relays to only one-hop communication and (ii) keeping inter-agent messages small, having each agent transmit only its own action information. Despite these information-access restrictions, our approach enables near-optimal action coordination by optimizing the agents' communication neighborhoods over time, through distributed online bandit optimization, subject to the agents' bandwidth constraints. Particularly, our approach enjoys an anytime suboptimality bound that is also strictly positive for arbitrary network topologies, even disconnected. To prove the bound, we define the Value of Coordination (VoC), an information-theoretic metric that quantifies for each agent the benefit of information access to its neighbors. We validate in simulations the scalability and near-optimality of our approach: it is observed to converge faster, outperform benchmarks for bandit submodular coordination, and can even outperform benchmarks that are privileged with a priori knowledge of the environment.

Problem

• distributed bandit optimization
• submodular coordination
• communication constraints
• multi-agent systems
• scalability

Innovation

• self-configurable mesh networks
• distributed submodular bandits
• one-hop communication
• Value of Coordination
• online bandit optimization