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

Fingerprint

Dynamic programming
dynamic programming
learning
Learning algorithms
Reinforcement learning
decision
programme
reinforcement

ASJC Scopus subject areas

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

Cite this

Si, J., Enns, R., & Wang, Y. T. (2001). Learning programs for decision and control. In 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings (Vol. 3, pp. 462-467). [983100] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICII.2001.983100

Learning programs for decision and control. / Si, Jennie; Enns, R.; Wang, Yu Tsung.

2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2001. p. 462-467 983100.

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

Si, J, Enns, R & Wang, YT 2001, Learning programs for decision and control. in 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings. vol. 3, 983100, Institute of Electrical and Electronics Engineers Inc., pp. 462-467, International Conferences on Info-Tech and Info-Net, ICII 2001, Beijing, China, 10/29/01. https://doi.org/10.1109/ICII.2001.983100
Si J, Enns R, Wang YT. Learning programs for decision and control. In 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings. Vol. 3. Institute of Electrical and Electronics Engineers Inc. 2001. p. 462-467. 983100 https://doi.org/10.1109/ICII.2001.983100
Si, Jennie ; Enns, R. ; Wang, Yu Tsung. / Learning programs for decision and control. 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings. Vol. 3 Institute of Electrical and Electronics Engineers Inc., 2001. pp. 462-467
@inproceedings{1553f3b9c7964557a97fc4ed2baefd03,
title = "Learning programs for decision and control",
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.",
author = "Jennie Si and R. Enns and Wang, {Yu Tsung}",
year = "2001",
doi = "10.1109/ICII.2001.983100",
language = "English (US)",
isbn = "0780370104",
volume = "3",
pages = "462--467",
booktitle = "2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Learning programs for decision and control

AU - Si, Jennie

AU - Enns, R.

AU - Wang, Yu Tsung

PY - 2001

Y1 - 2001

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84964501368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964501368&partnerID=8YFLogxK

U2 - 10.1109/ICII.2001.983100

DO - 10.1109/ICII.2001.983100

M3 - Conference contribution

AN - SCOPUS:84964501368

SN - 0780370104

SN - 9780780370104

VL - 3

SP - 462

EP - 467

BT - 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -