Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs 文章

ArXiv CS.AI2026-06-03NEWSen作者: Ali Asadi, Krishnendu Chatterjee, Ehsan Goharshady, Mehrdad Karrabi, Alipasha Montaseri, Carlo Pagano
查看原文 →
关系图谱

Strongly Polynomial Time Complexity of Policy Iteration for $L_\infty$ Robust MDPs · 相关技术

相关技术

discounted payoffsturn-based stochastic game$L_\infty$ uncertainty setslinear programmingL-infinity uncertainty setrobust MDPsMarkov Decision Processes