File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Performance evaluation of Double Action Q-learning in moving obstacle avoidance problem

TitlePerformance evaluation of Double Action Q-learning in moving obstacle avoidance problem
Authors
KeywordsObstacle avoidance
Q-learning
Reinforcement learning
Temporal differences
Issue Date2005
PublisherIEEE.
Citation
Conference Proceedings - Ieee International Conference On Systems, Man And Cybernetics, 2005, v. 1, p. 865-870 How to Cite?
AbstractThis paper describes the performance evaluation of Double-Action Q-learning in solving the moving obstacle avoidance problem. The evaluation is focused on two aspects: 1) obstacle avoidance, and 2) goal seeking; where four parameters are considered, namely, sum of rewards, no. of collisions, steps per episode, and obstacle density. Comparison is made between the new method and the traditional Q-learning method. Preliminary results show that the new method has the sum of rewards (negative) 29.4% and 93.6% less than that of the traditional method in an environment of 10 obstacles and 50 obstacles respectively. The mean no. of steps used in one episode is up to 26.0% lower than that of the traditional method. The new method also fares better as the number of obstacles increases. © 2005 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/45943
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorNgai, DCKen_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2007-10-30T06:39:08Z-
dc.date.available2007-10-30T06:39:08Z-
dc.date.issued2005en_HK
dc.identifier.citationConference Proceedings - Ieee International Conference On Systems, Man And Cybernetics, 2005, v. 1, p. 865-870en_HK
dc.identifier.issn1062-922Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/45943-
dc.description.abstractThis paper describes the performance evaluation of Double-Action Q-learning in solving the moving obstacle avoidance problem. The evaluation is focused on two aspects: 1) obstacle avoidance, and 2) goal seeking; where four parameters are considered, namely, sum of rewards, no. of collisions, steps per episode, and obstacle density. Comparison is made between the new method and the traditional Q-learning method. Preliminary results show that the new method has the sum of rewards (negative) 29.4% and 93.6% less than that of the traditional method in an environment of 10 obstacles and 50 obstacles respectively. The mean no. of steps used in one episode is up to 26.0% lower than that of the traditional method. The new method also fares better as the number of obstacles increases. © 2005 IEEE.en_HK
dc.format.extent346350 bytes-
dc.format.extent1832 bytes-
dc.format.extent10863 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofConference Proceedings - IEEE International Conference on Systems, Man and Cyberneticsen_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2005 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.en_HK
dc.subjectObstacle avoidanceen_HK
dc.subjectQ-learningen_HK
dc.subjectReinforcement learningen_HK
dc.subjectTemporal differencesen_HK
dc.titlePerformance evaluation of Double Action Q-learning in moving obstacle avoidance problemen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1062-922X&volume=1&spage=865&epage=870&date=2005&atitle=Performance+evaluation+of+double+action+Q-learning+in+moving+obstacle+avoidance+problemen_HK
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICSMC.2005.1571255en_HK
dc.identifier.scopuseid_2-s2.0-27944500194en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-27944500194&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume1en_HK
dc.identifier.spage865en_HK
dc.identifier.epage870en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridNgai, DCK=9332358900en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats