中国科学院数学与系统科学研究院期刊网
Last-Iterate Convergence to an Approximate Nash Equilibrium in Extensive-Form Games with Bandit Feedback and Variance Reduction
ZHU Kui, ZENG Xianlin, FANG Hao, HONG Yiguang
Journal of Systems Science & Complexity . 2026, (): 0 .