Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Generalized Dual Dynamic Programming for Infinite Horizon Problems in Continuous State and Action Spaces

Author(s):

J. Warrington, P. Beuchat, J. Lygeros
Conference/Journal:

Under review
Abstract:

We describe a nonlinear generalization of dual dynamic programming theory and its application to value function estimation for deterministic control problems over continuous state and action (or input) spaces, in a discrete-time infinite horizon setting. We prove that the result of a one-stage policy evaluation can be used to produce nonlinear lower bounds on the optimal value function that are valid over the entire state space. These bounds reflect the functional form of the system's costs, dynamics, and constraints. We provide an iterative algorithm that produces successively better approximations of the optimal value function, prove some key properties of the algorithm, and describe means of certifying the quality of the output. We demonstrate the efficacy of the approach on systems whose dimensions are too large for conventional dynamic programming approaches to be practical.

Further Information
Year:

2017
Type of Publication:

(01)Article
Supervisor:



File Download:

Request a copy of this publication.
(Uses JavaScript)
% Autogenerated BibTeX entry
@Article { WarBeu:2017:IFA_5736,
    author={J. Warrington and P. Beuchat and J. Lygeros},
    title={{Generalized Dual Dynamic Programming for Infinite Horizon
	  Problems in Continuous State and Action Spaces}},
    journal={NONE},
    year={2017},
    volume={},
    number={},
    pages={},
    month=nov,
    url={http://control.ee.ethz.ch/index.cgi?page=publications;action=details;id=5736}
}
Permanent link