{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:46:35Z","timestamp":1781279195522,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"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":[[2022,7]]},"DOI":"10.1109\/lra.2022.3180042","type":"journal-article","created":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T19:42:41Z","timestamp":1654285361000},"page":"7091-7098","source":"Crossref","is-referenced-by-count":9,"title":["Android as a Receptionist in a Shopping Mall Using Inverse Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1362-7940","authenticated-orcid":false,"given":"Zhichao","family":"Chen","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6307-5104","authenticated-orcid":false,"given":"Yutaka","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2062550"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3029798.3038301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-013-0180-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2702613.2702967"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2010.0233"},{"key":"ref6","first-page":"4565","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref7","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":"ref8","first-page":"362","article-title":"Risk-aware active inverse reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Brown","year":"2018"},{"key":"ref9","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref11","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Ng","year":"2000"},{"key":"ref12","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Pomerleau","year":"1989"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5772\/4876"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-39"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2017.00049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref17","first-page":"1","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu","year":"2018"},{"key":"ref18","first-page":"1","article-title":"SQIL: Imitation learning via reinforcement learning with sparse rewards","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddy","year":"2020"},{"key":"ref19","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref20","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2026508"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0006-8993(93)91758-K"},{"key":"ref25","article-title":"ultralytics\/yolov5: V6.0 - YOLOv5n nano models, roboflow integration, TensorFlow export, OpenCV DNN support","author":"G. J.","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_15"},{"key":"ref28","first-page":"1","article-title":"Whenet: Real-time fine-grained estimation for wide range head pose","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhou","year":"2020"},{"key":"ref29","article-title":"Playing atari with deep reinforcement learning","volume-title":"Proc. NIPS Deep Learn. Workshop","author":"Mnih","year":"2013"},{"key":"ref30","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref31","article-title":"Deep learning using rectified linear units (relu","author":"Agarap","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref33","first-page":"1","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kumar","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803357"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745086"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9750005\/09788067.pdf?arnumber=9788067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:27:43Z","timestamp":1706758063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9788067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":36,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3180042","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}