Hang Xu, Kai Li, Bingyun Liu, Haobo Fu, Qiang Fu...
TL;DR利用乐观的在线镜像下降算法最小化加权的对策后悔,从而加速收敛并解决博弈问题。
Abstract
counterfactual regret minimization (CFR) is a family of algorithms for
effectively solving imperfect-information games. It decomposes the total regret
into counterfactual regrets, utilizing local regret minimizat