Partitioning input space for reinforcement learning for control

D. F. Hougen, M. Gini, J. Slagle

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

8 Scopus citations

Abstract

This paper considers the effect of input-space partitioning on reinforcement learning for control. In many such learning systems, the input space is partitioned by the system designer. However, input-space partitioning could be learned. Our objective is to compare learned and fixed input-space partitionings in terms of the overall system learning speed and proficiency achieved. We present a system for unsupervised control-learning in temporal domains with results for both fixed and learned input-space partitionings. The trailer-backing task is used as an example problem.

Original languageEnglish (US)
Title of host publication1997 IEEE International Conference on Neural Networks, ICNN 1997
Pages755-760
Number of pages6
DOIs
StatePublished - Dec 1 1997
Event1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, United States
Duration: Jun 9 1997Jun 12 1997

Publication series

NameIEEE International Conference on Neural Networks - Conference Proceedings
Volume2
ISSN (Print)1098-7576

Other

Other1997 IEEE International Conference on Neural Networks, ICNN 1997
CountryUnited States
CityHouston, TX
Period6/9/976/12/97

Fingerprint Dive into the research topics of 'Partitioning input space for reinforcement learning for control'. Together they form a unique fingerprint.

Cite this