Hierarchical Learning-Based Control for Multi-Agent Shepherding of Stochastic Autonomous Agents

Multi-agent shepherding represents a challenging distributed control problem where herder agents must coordinate to guide independently moving targets to desired spatial configurations. Most existing control strategies assume cohesive target behavior, which frequently fails in practical applications where targets exhibit stochastic autonomous behavior. This paper presents a hierarchical learning-based control architecture that decomposes the shepherding problem into a high-level decision-making module and a low-level motion control component. The proposed distributed control system synthesizes effective control policies directly from closed-loop experience without requiring explicit inter-agent communication or prior knowledge of target dynamics. The decentralized architecture achieves cooperative control behavior through emergent coordination without centralized supervision. Experimental validation demonstrates superior closed-loop performance compared to state-of-the-art heuristic control methods, achieving 100% success rates with improved settling times and control efficiency. The control architecture scales beyond its design conditions, adapts to time-varying goal regions, and demonstrates practical implementation feasibility through real-time experiments on the Robotarium platform.