Regularization is Enough for Last-Iterate Convergence in Zero-Sum GamesZongkai Liu, Chaohao Hu,Chao Yu,Peng SunICLR 2024（2024）引用 0|浏览4关键词two-player zero-sum games,reinforcement learning,last-iterate convergenceAI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
