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.

翻译：本研究探讨在带宽、数据速率和连通性等现实通信约束下，如何实现分布式赌博机次模协调的可扩展性。研究动机源于未知、部分可观测且资源受限环境中多智能体主动态势感知任务，此类任务要求智能体必须通过点对点通信进行协调。我们的方法通过以下机制实现可扩展性：(i) 将信息中继限制在单跳通信范围内；(ii)保持智能体间消息小型化，使每个智能体仅传输自身动作信息。尽管存在这些信息访问限制，我们的方法通过在智能体带宽约束条件下，通过分布式在线赌博机优化动态优化智能体的通信邻域，实现了近乎最优的动作协调。特别值得注意的是，该方法具备随时次优性界，且该界限对于任意网络拓扑（包括非连通网络）均保持严格正值。为证明该界限，我们定义了协调价值——一种信息论度量指标，用于量化每个智能体访问邻居信息所获得的收益。我们通过仿真验证了该方法在可扩展性和近优性方面的优势：观测到该方法具有更快的收敛速度，在赌博机次模协调任务中超越基准方法，甚至能够优于那些具备环境先验知识的基准方法。