Limiting average criteria for nonstationary Markov decision processes

作者：Guo, XP^*; Shi, P

来源：SIAM Journal on Optimization, 2001, 11(4): 1037-1053.

DOI：10.1137/S1052623499355235

• nonstationary Markov decision processes
• limiting average criteria
• optimality equations
• limiting average epsilon-optimal policies
• rolling horizon algorithm

This paper deals with the so-called limiting average criteria for nonstationary Markov decision processes with (possibly unbounded) rewards and Borel state space. A new set of conditions is provided, under which the existence of both a solution to the optimality equations and the limiting average epsilon(greater than or equal to 0)-optimal Markov policies is derived. Also, a rolling horizon algorithm for computing limiting average epsilon( > 0)-optimal Markov policies is developed. Furthermore, the results in this paper are illustrated by several examples such as the water regulation problem.

• 出版日期2001-4-24
• 单位中山大学