Multi-Agent Reinforcement Learning with Control-Theoretic Safety Guarantees for Dynamic Network Bridging

arXiv:2404.01551v1 Announce Type: cross
Abstract: Addressing complex cooperative tasks in safety-critical environments poses significant challenges for Multi-Agent Systems, especially under conditions of partial observability. This work introduces a hybrid approach that integrates Multi-Agent Reinforcement Learning with control-theoretic methods to ensure safe and efficient distributed strategies. Our contributions include a novel setpoint update algorithm that dynamically adjusts agents' positions to preserve safety conditions without compromising the mission's objectives. Through experimental validation, we demonstrate significant advantages over conventional MARL strategies, achieving comparable …

abstract agent arxiv challenges control cs.ai cs.lg cs.ma cs.ni cs.sy distributed dynamic eess.sy environments hybrid hybrid approach multi-agent network observability reinforcement reinforcement learning safe safety safety-critical strategies systems tasks type work