File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Response knowledge learning of autonomous agent

TitleResponse knowledge learning of autonomous agent
Authors
Chow, C-KTsui, H-T
Issue Date2004
PublisherInstitute of Electrical and Electronics Engineers. The Journals web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500
Citation
The 2004 IEEE International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, 25-29 July 2004. In IEEE International Conference on Neural Networks Proceedings, 2004, v. 2, p. 1133-1138 How to Cite?
DOI: http://dx.doi.org/10.1109/IJCNN.2004.1380094
AbstractIn robot applications, the performance of a robot agent is measured by the quantity of award received from its response. Many literatures [1-5] define the response as either a state diagram or a neural network. Due to the absence of a desired response, neither of them is applicable to an unstructural environment. In this paper, a novel Response Knowledge Learning algorithm is proposed to handle this domain. By using a set of experiences, the algorithm can extract the contributed experiences to construct the response function. Two sets of environments are provided to illustrate the performance of the proposed algorithm. The results show that it can effectively construct the response function that receives an award which is very close to the true maximum.
Persistent Identifierhttp://hdl.handle.net/10722/196646
ISBN
0-7803-8359-1
ISSN
1098-7576

 

DC FieldValueLanguage
dc.contributor.authorChow, C-K-
dc.contributor.authorTsui, H-T-
dc.date.accessioned2014-04-24T02:10:30Z-
dc.date.available2014-04-24T02:10:30Z-
dc.date.issued2004-
dc.identifier.citationThe 2004 IEEE International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary, 25-29 July 2004. In IEEE International Conference on Neural Networks Proceedings, 2004, v. 2, p. 1133-1138-
dc.identifier.isbn0-7803-8359-1-
dc.identifier.issn1098-7576-
dc.identifier.urihttp://hdl.handle.net/10722/196646-
dc.description.abstractIn robot applications, the performance of a robot agent is measured by the quantity of award received from its response. Many literatures [1-5] define the response as either a state diagram or a neural network. Due to the absence of a desired response, neither of them is applicable to an unstructural environment. In this paper, a novel Response Knowledge Learning algorithm is proposed to handle this domain. By using a set of experiences, the algorithm can extract the contributed experiences to construct the response function. Two sets of environments are provided to illustrate the performance of the proposed algorithm. The results show that it can effectively construct the response function that receives an award which is very close to the true maximum.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journals web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000500-
dc.relation.ispartofIEEE International Conference on Neural Networks Proceedings-
dc.rights©2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.titleResponse knowledge learning of autonomous agent-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/IJCNN.2004.1380094-
dc.identifier.scopuseid_2-s2.0-10944254097-
dc.identifier.volume2-
dc.identifier.spage1133-
dc.identifier.epage1138-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 160603 amended-
dc.identifier.issnl1098-7576-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats