{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:14:53Z","timestamp":1771956893500,"version":"3.50.1"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JST, Moonshot R&D","award":["JPMJMS2011"],"award-info":[{"award-number":["JPMJMS2011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/lra.2023.3267385","type":"journal-article","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T17:32:40Z","timestamp":1681493560000},"page":"3350-3357","source":"Crossref","is-referenced-by-count":11,"title":["Outperformance of Mall-Receptionist Android as Inverse Reinforcement Learning is Transitioned to Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1362-7940","authenticated-orcid":false,"given":"Zhichao","family":"Chen","sequence":"first","affiliation":[{"name":"Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6307-5104","authenticated-orcid":false,"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Behavior Learning Research Team, Guardian Robot Project, RIKEN, Saitama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-7648","authenticated-orcid":false,"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2016"},{"key":"ref2","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho","year":"2016"},{"key":"ref3","first-page":"3909","article-title":"Cooperative inverse reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hadfield-Menell","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180042"},{"key":"ref6","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Brown"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","article-title":"Solving rubiks cube with a robot hand","author":"Akkaya","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2412554"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"ref14","first-page":"1","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu","year":"2016"},{"key":"ref15","first-page":"9465","article-title":"RRL: Resnet as representation for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Shah","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4002715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iros55552.2023.10342038"},{"key":"ref19","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref21","first-page":"1331","article-title":"Distilling policy distillation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Czarnecki","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10102643\/10102484.pdf?arnumber=10102484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:41:43Z","timestamp":1723056103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10102484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":22,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3267385","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}