Approximate dynamic programming via iterated Bellman inequalities

Yan Wang, Brendan O’Donoghue, Stephen BoydInternational Journal of Robust and Nonlinear Control 2014 · DOI

Abstract

Summary In this paper, we introduce new methods for finding functions that lower bound the value function of a stochastic control problem, using an iterated form of the Bellman inequality. Our method is based on solving linear or semidefinite programs, and produces both a bound on the optimal objective, as well as a suboptimal policy that appears to works very well. These results extend and improve bounds obtained in a previous paper using a single Bellman inequality condition. We describe the methods in a general setting and show how they can be applied in specific cases including the finite state case, constrained linear quadratic control, switched affine control, and multi‐period portfolio investment. Copyright © 2014 John Wiley & Sons, Ltd.
BibTeX
@article{wang2014approximate,
  author = {Yan Wang and Brendan O’Donoghue and Stephen Boyd},
  title = {{Approximate dynamic programming via iterated Bellman inequalities}},
  journal = {International Journal of Robust and Nonlinear Control},
  year = {2014},
  doi = {10.1002/rnc.3152},
}

Loading related content...

Figure