Tag
该论文介绍了IR-PRM+结合前一效用预测(previous-utility prediction)的新方法，为有限两人零和矩阵博弈中的同时和交替更新恢复了常数遗憾和收敛率保证，包括与T无关的外部遗憾、O(T⁻¹)平均对偶间隙和O(T⁻¹/²)最优迭代间隙，并将分析扩展到扩展式博弈的CFR变体IR-PCFR+。
EMAgnet introduces parameter-space exponential moving average regularization for policy gradient self-play in large two-player zero-sum games, achieving lower exploitability compared to uniform regularization targets.