Non-Parametric Approximate Dynamic Programming via the Kernel Method

This paper presents a novel non-parametric approximate dynamic programming (ADP) algorithm that enjoys graceful approximation and sample complexity guarantees. In particular, we establish both theoretically and computationally that our proposal can serve as a viable alternative to state-of-the-art p...

Full description

Bibliographic Details
Main Authors: Bhat, Nikhil (Author), Farias, Vivek F. (Contributor), Moallemi, Ciamac C. (Author)
Other Authors: Sloan School of Management (Contributor)
Format: Article
Language:English
Published: Neural Information Processing Systems Foundation, 2014-09-11T12:56:58Z.
Subjects:
Online Access:Get fulltext
Description
Summary:This paper presents a novel non-parametric approximate dynamic programming (ADP) algorithm that enjoys graceful approximation and sample complexity guarantees. In particular, we establish both theoretically and computationally that our proposal can serve as a viable alternative to state-of-the-art parametric ADP algorithms, freeing the designer from carefully specifying an approximation architecture. We accomplish this by developing a kernel-based mathematical program for ADP. Via a computational study on a controlled queueing network, we show that our procedure is competitive with parametric ADP approaches.