Premium
ERROR BOUNDS FOR CALCULATION OF THE GITTINS INDICES
Author(s) -
Wang YouGan
Publication year - 1997
Publication title -
australian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 0004-9581
DOI - 10.1111/j.1467-842x.1997.tb00538.x
Subject(s) - bernoulli's principle , markov decision process , class (philosophy) , exponential function , mathematical optimization , computer science , bernoulli trial , calibration , dynamic programming , mathematics , markov process , algorithm , artificial intelligence , statistics , mathematical analysis , engineering , aerospace engineering
summary For a wide class of semi‐Markov decision processes the optimal policies are expressible in terms of the Gittins indices, which have been found useful in sequential clinical trials and pharmaceutical research planning. In general, the indices can be approximated via calibration based on dynamic programming of finite horizon. This paper provides some results on the accuracy of such approximations, and, in particular, gives the error bounds for some well known processes (Bernoulli reward processes, normal reward processes and exponential target processes).