Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanovic. Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning. In Nikolai Matni, Manfred Morari, George J. Pappas, editors, Learning for Dynamics and Control Conference, L4DC 2023, 15-16 June 2023, Philadelphia, PA, USA. Volume 211 of Proceedings of Machine Learning Research, pages 315-332, PMLR, 2023. [doi]
Abstract is missing.