TY - JOUR
AU - Van Roy, B.
AB - The curse of dimensionality gives rise to prohibitive computational requirements that render infeasible the exact solution of large-scale stochastic control problems. We study an efficient method based on linear programming for approximating solutions to such problems. The approach fits a linear combination of pre-selected basis functions to the dynamic programming cost-to-go function. We develop error bounds that offer performance guarantees and also guide the selection of both basis functions and state-relevance weights that influence quality of the approximation. Experimental results in the domain of queueing network control provide empirical support for the methodology.
TI - The Linear Programming Approach to Approximate Dynamic Programming
JF - Operations Research
DO - 10.1287/opre.51.6.850.24925
DA - 2003-12-01
UR - https://www.deepdyve.com/lp/informs/the-linear-programming-approach-to-approximate-dynamic-programming-FnbEuib4Rv
SP - 850
EP - 865
VL - 51
IS - 6
DP - DeepDyve
ER -