Abstract
Whittle enunciated an important reduction principle in dynamic programming when he showed that under certain conditions optimal strategies for Markov decision processes (MDPs) placed in parallel to one another take actions in a way which is consistent with the optimal strategies for the individual MDPs. However, the necessary and sufficient conditions given by Whittle are by no means always satisfied. We explore the status of this computationally attractive reduction principle when these conditions fail.
Publisher
Cambridge University Press (CUP)
Subject
Applied Mathematics,Statistics and Probability
Reference15 articles.
1. Glazebrook K. D. (1987) Evaluating strategies for Markov decision processes in parallel (submitted).
2. Stoppable families of alternative bandit processes
3. On the scheduling of alternative stochastic jobs on a single machine
4. Nash P. (1973) Optimal Allocation of Resources Between Research Projects. Ph.D. thesis, Cambridge University.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献