BriefGPT.xyz
Mar, 2022
对抗对手下的学习马尔科夫博弈:高效算法与基本极限
Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits
HTML
PDF
Qinghua Liu, Yuanhao Wang, Chi Jin
TL;DR
本文研究了在零和游戏中应用没有遗憾学习算法对抗自适应对手并取得最优结果的问题,并给出了一组正负结果,其中提出的新算法在普通的策略类别小或对手策略类别小时,可取得平均的regret较小的结果。
Abstract
An ideal strategy in
zero-sum games
should not only grant the player an average reward no less than the value of Nash equilibrium, but also exploit the (adaptive) opponents when they are suboptimal. While most existing works in
→