发表机构
Georgia Institute of Technology; Yale University; Google Research(佐治亚理工学院; 耶鲁大学; 谷歌研究院)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文构造了一族两人零和博弈,证明虚构博弈可达到任意慢的多项式收敛速率,并推广了Wang(2025)的结果,为Karlin猜想提供反例。
AI 中文摘要
我们证明在两人零和博弈中,虚构博弈可以以任意慢的多项式速率收敛。对于每个整数 $k \ge 2$,我们构造一个每个玩家有 $(k+1)^2 - 5$ 个动作的支付矩阵,使得经验策略的对偶间隙在 $t$ 步后以 $\Theta(t^{-1/k})$ 衰减。该族从标准石头-剪刀-布矩阵开始,每个更高阶的博弈从前一个博弈递归构造。在规定的共同初始动作之后,虚构博弈下的每个后续最优响应都是唯一的。对于 $k \ge 3$,这些博弈给出了 Karlin 推测的 $O(t^{-1/2})$ 收敛速率的反例,并将 Wang (2025) 最近的 $\Theta(t^{-1/3})$ 构造扩展到任意慢的多项式速率。
英文摘要
We show that fictitious play can converge at arbitrarily slow polynomial rates in two-player zero-sum games. For every integer $k \ge 2$, we construct a payoff matrix with $(k+1)^2 - 5$ actions per player for which the duality gap of the empirical strategies decays as $Θ(t^{-1/k})$ after $t$ steps. The family starts from the standard rock-paper-scissors matrix, with each higher-order game constructed recursively from the preceding one. After a prescribed common initial action, every subsequent best response under fictitious play is unique. For $k \ge 3$, these games give counterexamples to Karlin's conjectured $O(t^{-1/2})$ convergence rate, and they extend the recent $Θ(t^{-1/3})$ construction of Wang (2025) to arbitrarily slow polynomial rates.