Asynchronous Distributed Bandit Submodular Maximization under Heterogeneous Communication Delays

2026-04-07

AI Summary

This study addresses the challenge of cooperative decision-making among heterogeneous multi-agent systems operating in unknown environments, where asynchronous local clocks and communication delays impede coordination. The authors propose an asynchronous distributed coordination algorithm that relies solely on single-hop neighbor communication and achieves scalable, near-optimal decisions within a constrained submodular optimization framework. This work provides the first theoretical approximation guarantees for distributed submodular maximization under asynchronous and heterogeneous delay conditions, explicitly characterizing the impact of communication delays, clock offsets, and network topology on performance. Furthermore, it establishes a bound on the suboptimality relative to the ideal synchronous centralized solution. Simulations demonstrate the algorithm’s high effectiveness and robustness in multi-camera area monitoring tasks.

Abstract

We study asynchronous distributed decision-making for scalable multi-agent bandit submodular maximization. We are motivated by distributed information-gathering tasks in unknown environments and under heterogeneous inter-agent communication delays. To enable scalability despite limited communication delays, existing approaches restrict each agent to coordinate only with its one-hop neighbors. But these approaches assume homogeneous communication delays among the agents and a synchronous global clock. In practice, however, delays are heterogeneous, and agents operate with mismatched local clocks. That is, each agent does not receive information from all neighbors at the same time, compromising decision-making. In this paper, we provide an asynchronous coordination algorithm to overcome the challenges. We establish a provable approximation guarantee against the optimal synchronized centralized solution, where the suboptimality gap explicitly depends on communication delays and clock mismatches. The bounds also depend on the topology of each neighborhood, capturing the effect of distributed decision-making via one-hop-neighborhood messages only. We validate the approach through numerical simulations on multi-camera area monitoring.

Problem

• asynchronous distributed decision-making
• heterogeneous communication delays
• bandit submodular maximization
• clock mismatches
• multi-agent coordination

Innovation

• asynchronous coordination
• heterogeneous communication delays
• bandit submodular maximization
• distributed decision-making
• approximation guarantee