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

TL;DR

This paper introduces a scalable, communication-efficient distributed bandit algorithm for multi-agent submodular optimization that adapts over time to optimize coordination in resource-limited, partially observable environments.

Contribution

It proposes a novel self-configurable mesh network approach that limits communication to one-hop and optimizes neighborhoods online, achieving near-optimal coordination under bandwidth constraints.

Findings

Faster convergence in simulations compared to benchmarks.

Outperforms benchmarks with prior environmental knowledge.

Maintains positive suboptimality bounds across network topologies.

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.