Learning programs for decision and control

Jennie Si, R. Enns, Yu Tsung Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Introduces learning programs, an approximate dynamic programming (ADP) or otherwise named neural dynamic programming (NDP) algorithm developed and tested by the authors. We first introduce the basic framework of our learning programs, the associated learning algorithms, and then extensive case studies to demonstrate the effectiveness of our learning programs. This is probably the first time that neural dynamic programming type of learning algorithms has been applied to complex, real life continuous state problems. Until now, reinforcement learning (another learning approach for approximate dynamic programming) has been mostly successful in discrete state space problems. On the other hand, prior NDP based approaches to controlling continuous state space systems have all been limited to smaller, or linearized, or decoupled problems. Therefore the work presented here compliments and advances the existing literature in the general area of learning approaches in approximate dynamic programming.

Original languageEnglish (US)
Title of host publication2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages462-467
Number of pages6
Volume3
ISBN (Print)0780370104, 9780780370104
DOIs
StatePublished - 2001
EventInternational Conferences on Info-Tech and Info-Net, ICII 2001 - Beijing, China
Duration: Oct 29 2001Nov 1 2001

Other

OtherInternational Conferences on Info-Tech and Info-Net, ICII 2001
CountryChina
CityBeijing
Period10/29/0111/1/01

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Computers in Earth Sciences
  • Control and Systems Engineering
  • Instrumentation

Fingerprint Dive into the research topics of 'Learning programs for decision and control'. Together they form a unique fingerprint.

Cite this