Min Cheng, Ruida Zhou, P. R. Kumar 0001, Chao Tian 0002. Provable Policy Gradient Methods for Average-Reward Markov Potential Games. In Sanjoy Dasgupta, Stephan Mandt, Yingzhen Li, editors, International Conference on Artificial Intelligence and Statistics, 2-4 May 2024, Palau de Congressos, Valencia, Spain. Volume 238 of Proceedings of Machine Learning Research, pages 4699-4707, PMLR, 2024. [doi]
Abstract is missing.