solidot新版网站常见问题,请点击这里查看。
消息
本文已被查看3630次
Convex and Lipschitz function approximations for Markov decision processes. (arXiv:1712.00970v2 [math.OC] UPDATED)
来源于:arXiv
This paper studies the use of convex Lipschitz continuous functions to
approximate the value functions in Markov decision processes containing a
finite number of possible actions. Compact convergence is proved under various
sampling schemes for the driving state disturbance. Under some assumptions,
these approximations give a non-decreasing sequence of lower bounding or a
non-increasing sequence of upper bounding functions. Numerical experiments
involving piecewise linear approximations for a Bermudan put option demonstrate
that tight bounding functions for its fair price over the entire state space
can be obtained with excellent speed (fractions of a cpu second). 查看全文>>