Efficient learning and planning within the dyna framework

Jing Peng, Ronald J. Williams

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

6 Citations (Scopus)

Abstract

Sutton's Dyna framework provides a novel and computationally appealing way to create integrated learning, planning, and reacting systems. Examined here is a class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency. The benefit of using these strategies is demonstrated on some simple abstract learning tasks.

Original languageEnglish
Title of host publication1993 IEEE International Conference on Neural Networks, ICNN 1993
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages168-174
Number of pages7
Volume1993-January
ISBN (Electronic)0780309995
DOIs
StatePublished - 1 Jan 1993
EventIEEE International Conference on Neural Networks, ICNN 1993 - San Francisco, United States
Duration: 28 Mar 19931 Apr 1993

Other

OtherIEEE International Conference on Neural Networks, ICNN 1993
CountryUnited States
CitySan Francisco
Period28/03/931/04/93

Fingerprint

Planning
Computational efficiency

Cite this

Peng, J., & Williams, R. J. (1993). Efficient learning and planning within the dyna framework. In 1993 IEEE International Conference on Neural Networks, ICNN 1993 (Vol. 1993-January, pp. 168-174). [298551] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICNN.1993.298551
Peng, Jing ; Williams, Ronald J. / Efficient learning and planning within the dyna framework. 1993 IEEE International Conference on Neural Networks, ICNN 1993. Vol. 1993-January Institute of Electrical and Electronics Engineers Inc., 1993. pp. 168-174
@inproceedings{1337aa99e63044a59deeb6d49fea523e,
title = "Efficient learning and planning within the dyna framework",
abstract = "Sutton's Dyna framework provides a novel and computationally appealing way to create integrated learning, planning, and reacting systems. Examined here is a class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency. The benefit of using these strategies is demonstrated on some simple abstract learning tasks.",
author = "Jing Peng and Williams, {Ronald J.}",
year = "1993",
month = "1",
day = "1",
doi = "10.1109/ICNN.1993.298551",
language = "English",
volume = "1993-January",
pages = "168--174",
booktitle = "1993 IEEE International Conference on Neural Networks, ICNN 1993",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Peng, J & Williams, RJ 1993, Efficient learning and planning within the dyna framework. in 1993 IEEE International Conference on Neural Networks, ICNN 1993. vol. 1993-January, 298551, Institute of Electrical and Electronics Engineers Inc., pp. 168-174, IEEE International Conference on Neural Networks, ICNN 1993, San Francisco, United States, 28/03/93. https://doi.org/10.1109/ICNN.1993.298551

Efficient learning and planning within the dyna framework. / Peng, Jing; Williams, Ronald J.

1993 IEEE International Conference on Neural Networks, ICNN 1993. Vol. 1993-January Institute of Electrical and Electronics Engineers Inc., 1993. p. 168-174 298551.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Efficient learning and planning within the dyna framework

AU - Peng, Jing

AU - Williams, Ronald J.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - Sutton's Dyna framework provides a novel and computationally appealing way to create integrated learning, planning, and reacting systems. Examined here is a class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency. The benefit of using these strategies is demonstrated on some simple abstract learning tasks.

AB - Sutton's Dyna framework provides a novel and computationally appealing way to create integrated learning, planning, and reacting systems. Examined here is a class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency. The benefit of using these strategies is demonstrated on some simple abstract learning tasks.

UR - http://www.scopus.com/inward/record.url?scp=84943269745&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1993.298551

DO - 10.1109/ICNN.1993.298551

M3 - Conference contribution

VL - 1993-January

SP - 168

EP - 174

BT - 1993 IEEE International Conference on Neural Networks, ICNN 1993

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Peng J, Williams RJ. Efficient learning and planning within the dyna framework. In 1993 IEEE International Conference on Neural Networks, ICNN 1993. Vol. 1993-January. Institute of Electrical and Electronics Engineers Inc. 1993. p. 168-174. 298551 https://doi.org/10.1109/ICNN.1993.298551