{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T14:05:18Z","timestamp":1748527518469,"version":"3.37.3"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3331373","type":"journal-article","created":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T19:07:01Z","timestamp":1699470421000},"page":"126524-126541","source":"Crossref","is-referenced-by-count":1,"title":["Policy Optimization for Waste Crane Automation From Human Preferences"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9058-1379","authenticated-orcid":false,"given":"Yuhwan","family":"Kwon","sequence":"first","affiliation":[{"name":"Robot Learning Laboratory, Division of Information Sciences, Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6974-0726","authenticated-orcid":false,"given":"Hikaru","family":"Sasaki","sequence":"additional","affiliation":[{"name":"Robot Learning Laboratory, Division of Information Sciences, Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1040-3455","authenticated-orcid":false,"given":"Terushi","family":"Hirabayashi","sequence":"additional","affiliation":[{"name":"Hitachi Zosen Corporation, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6281-7276","authenticated-orcid":false,"given":"Kaoru","family":"Kawabata","sequence":"additional","affiliation":[{"name":"Hitachi Zosen Corporation, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3545-4814","authenticated-orcid":false,"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Robot Learning Laboratory, Division of Information Sciences, Nara Institute of Science and Technology, Nara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SCIS-ISIS.2018.00116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3002204"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811781"},{"key":"ref4","article-title":"Concrete problems in AI safety","author":"Amodei","year":"2016","journal-title":"arXiv:1606.06565"},{"key":"ref5","first-page":"1","article-title":"The ingredients of real world robotic reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596494"},{"key":"ref7","first-page":"1282","article-title":"Preferential Bayesian optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Gonz\u00e1lez"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2021.104119"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2016.05.009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21654"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969944"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462923"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3152865"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.03.015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2005.06.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00097-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/1077546309103421"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/00207170310001604954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1093\/jcde\/qwac063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104620"},{"key":"ref22","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Christiano"},{"key":"ref23","first-page":"6152","article-title":"PEBBLE: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Lee"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084198"},{"key":"ref25","first-page":"1","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref26","first-page":"2014","article-title":"Few-shot preference learning for human-in-the-loop RL","volume-title":"Proc. The 6th Conf. Robot Learn. (CoRL)","volume":"205","author":"Hejna"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.041"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968522"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196661"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341416"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05935-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/ECC54610.2021.9654900"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3094479"},{"key":"ref35","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"2","author":"Snoek"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102369"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.08-07-592"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3207560"},{"volume-title":"The Oxford Handbook of Cognitive Science","year":"2017","author":"Chipman","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref42","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ita50056.2020.9244936"},{"key":"ref44","first-page":"1177","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"100","author":"Biyik"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05867-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433420"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10313266.pdf?arnumber=10313266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:05:06Z","timestamp":1710381906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10313266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3331373","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}