Deep imitation learning: the impact of depth on policy performance

Kebria, Parham M, Khosravi, Abbas, Salaken, Syed Moshfeq, Hossain, Ibrahim, Kabir, Hussain Mohammed Dipu, Koohestani, Afsaneh, Alizadehsani, Roohallah and Nahavandi, Saeid 2018, Deep imitation learning: the impact of depth on policy performance, in ICONIP 2018 : Proceedings of the 25th International Conference on Neural Information Processing, Springer, Cham, Switzerland, pp. 172-181, doi: 10.1007/978-3-030-04167-0_16.

Attached Files
Name Description MIMEType Size Downloads

Title Deep imitation learning: the impact of depth on policy performance
Author(s) Kebria, Parham M
Khosravi, AbbasORCID iD for Khosravi, Abbas orcid.org/0000-0001-6927-0744
Salaken, Syed MoshfeqORCID iD for Salaken, Syed Moshfeq orcid.org/0000-0001-8632-2665
Hossain, Ibrahim
Kabir, Hussain Mohammed DipuORCID iD for Kabir, Hussain Mohammed Dipu orcid.org/0000-0002-3395-1772
Koohestani, Afsaneh
Alizadehsani, Roohallah
Nahavandi, SaeidORCID iD for Nahavandi, Saeid orcid.org/0000-0002-0360-5270
Conference name Asia Pacific Neural Network Society. Conference (25th : 2018 : Siem Reap, Cambodia)
Conference location Siem Reap, Cambodia
Conference dates 2018/12/13 - 2018/12/16
Title of proceedings ICONIP 2018 : Proceedings of the 25th International Conference on Neural Information Processing
Editor(s) Cheng, Long
Leung, Andrew Chi Sing
Ozawa, Seiichi
Publication date 2018
Series Asia Pacific Neural Network Society Conference
Start page 172
End page 181
Total pages 10
Publisher Springer
Place of publication Cham, Switzerland
Keyword(s) Autonomous vehicle
Imitation learning
Simulation Depth
ISBN 9783030041663
ISSN 0302-9743
1611-3349
Language eng
DOI 10.1007/978-3-030-04167-0_16
Field of Research 08 Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2018, Springer Nature Switzerland AG
Persistent URL http://hdl.handle.net/10536/DRO/DU:30123289

Document type: Conference Paper
Collections: Centre for Intelligent Systems Research
GTP Research
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 1 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 27 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Tue, 25 Jun 2019, 14:55:52 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.