Non-Parametric Approximate Dynamic Programming via the Kernel Method
Name
Farias_Non-parametric.pdf
Size
581.42 KB
Format
Adobe PDF
Checksum (MD5)
ab4da54139a003453ed232c717339d25
Author(s)
Bhat, Nikhil
Farias, Vivek F.
Moallemi, Ciamac C.
Date Issued
December 2012
Journal
Proceedings of the 2012 Neural Information Processing Systems Conference
Publisher
Neural Information Processing Systems Foundation
Citation
Bhat, Nikhil, Vivek F. Farias, and Ciamac C. Moallemi. "Non-Parametric Approximate Dynamic Programming via the Kernel Method." The 2012 Neural Information Processing Systems Conference, Lake Tahoe, Nevada, December 3-8, 2012.
Version
Author's final manuscript
Abstract
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.
MIT Department
Sloan School of Management
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://nips.cc/Conferences/2012/Program/event.php?ID=3284
