{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T13:26:48Z","timestamp":1762954008712,"version":"3.37.3"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["#2024936"],"award-info":[{"award-number":["#2024936"]}]},{"name":"Agilent Early Career Professor Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/lra.2024.3415432","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T18:26:37Z","timestamp":1718648797000},"page":"6896-6903","source":"Crossref","is-referenced-by-count":1,"title":["Selecting Source Tasks for Transfer Learning of Human Preferences"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6806-9704","authenticated-orcid":false,"given":"Heramb","family":"Nemlekar","sequence":"first","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0781-8772","authenticated-orcid":false,"given":"Naren","family":"Sivagnanadasan","sequence":"additional","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3484-9427","authenticated-orcid":false,"given":"Subham","family":"Banga","sequence":"additional","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0275-1823","authenticated-orcid":false,"given":"Neel","family":"Dhanaraj","sequence":"additional","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6025-7903","authenticated-orcid":false,"given":"Satyandra K.","family":"Gupta","sequence":"additional","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1081-250X","authenticated-orcid":false,"given":"Stefanos","family":"Nikolaidis","sequence":"additional","affiliation":[{"name":"Viterbi School of Engineering, Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3576965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515526"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN53752.2022.9900872"},{"key":"ref4","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. 23rd AAAI Conf. Artif. Intell.","author":"Ziebart","year":"2008"},{"key":"ref5","article-title":"Repeated inverse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Kareem","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082482"},{"key":"ref7","first-page":"181","article-title":"Policy transfer using reward shaping","volume-title":"Proc. 14th Int. Conf. Auton. Agents Multiagent Syst.","author":"Brys","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-017-0089-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8205959"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057050"},{"issue":"7","key":"ref11","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989108"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103551"},{"key":"ref14","first-page":"672","article-title":"General game learning using knowledge transfer","volume-title":"Proc. 20th Int. Joint Conf. Artif. Intell.","author":"Banerjee","year":"2007"},{"key":"ref15","first-page":"17","article-title":"Deep learning of representations for unsupervised and transfer learning","volume-title":"Proc. ICML Workshop Unsupervised Transfer Learn.","author":"Bengio","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3277905"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555955"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref19","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng","year":"2000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.693050"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10561888\/10559410-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10561888\/10559410.pdf?arnumber=10559410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:32:43Z","timestamp":1734982363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10559410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":20,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3415432","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}