TY - GEN
T1 - Learning programs for decision and control
AU - Si, Jennie
AU - Enns, R.
AU - Wang, Yu Tsung
N1 - Funding Information:
Research supported by NSF under grants ECS-9553202 and ECS-0002098,a nd in part by Motorola.
Funding Information:
Research supported by NSF under grants ECS-9553202 and ECS-0002098, and in part by Motorola. The third author is now with Scientific Monitoring, Inc. in Tempe, Arizona.
Publisher Copyright:
© 2001 IEEE.
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
T3 - 2001 International Conferences on Info-Tech and Info-Net: A Key to Better Life, ICII 2001 - Proceedings
SP - 462
EP - 467
BT - 2001 International Conferences on Info-Tech and Info-Net
A2 - Shi, Zhongzhi
A2 - Li, Hui
A2 - Zhong, Y.X.
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - International Conferences on Info-Tech and Info-Net, ICII 2001
Y2 - 29 October 2001 through 1 November 2001
ER -