一类s-矩形鲁棒MDP:相对保守性、渐近分析与有限样本性质

A Family of \(\boldsymbol{s}\)-Rectangular Robust MDPs: Relative Conservativeness, Asymptotic Analyses, and Finite-Sample Properties

SIAM Journal on Optimization · 2024
被引 1
ABS 3
鲁棒优化马尔可夫决策过程渐近分析有限样本性质