Optimally solving Markov decision processes with total expected discounted reward function: Linear programming revisited |
| |
Affiliation: | 1. INRIA-Saclay, Palaiseau 91192, France;2. Department of Aeronautics and Astronautics, University of Washington, Seattle, WA 98195, USA;3. Inria Sophia Antipolis, 2004 Route des Lucioles, B.P. 93, 06902 Sophia Antipolis Cedex, France;4. Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, LIP6, F-75005 Paris, France |
| |
Abstract: | We compare the computational performance of linear programming (LP) and the policy iteration algorithm (PIA) for solving discrete-time infinite-horizon Markov decision process (MDP) models with total expected discounted reward. We use randomly generated test problems as well as a real-life health-care problem to empirically show that, unlike previously reported, barrier methods for LP provide a viable tool for optimally solving such MDPs. The dimensions of comparison include transition probability matrix structure, state and action size, and the LP solution method. |
| |
Keywords: | Markov decision process MDP Linear programming Policy iteration Total expected discounted reward Treatment optimization |
本文献已被 ScienceDirect 等数据库收录! |
|