Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

The article presents a hierarchical multi-agent reinforcement learning (MARL) framework that integrates constraint manifold control to enforce hard safety constraints while enabling coordination among agents. This approach provides theoretical safety guarantees and achieves stationary learning dynamics, leading to stable and efficient training. Empirical results demonstrate competitive performance with nearly perfect safety rates, making it significant for practitioners focused on safety-critical applications in multi-agent systems.