A Linearly Relaxed Approximate Linear Program for Markov Decision Processes

Abstract

Approximate linear programming (ALP) and its variants have been widely applied to Markov Decision Processes (MDPs) with a large number of states. A serious limitation of ALP is that it has an intractable number of constraints, as a result of which constraint approximations are of interest. In this paper, we define a linearly relaxed approximation linear program (LRALP) that has a tractable number of constraints, obtained as positive linear combinations of the original constraints of the ALP. The main contribution is a novel performance bound for LRALP.

23 pages, 2 figures, submitted to IEEE TAC

References in corpus (2)

• Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes
• Linear Programming for Large-Scale Markov Decision Problems

Cited by in corpus (1)

• Offline Policy Selection under Uncertainty