{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:13:20Z","timestamp":1740176000863,"version":"3.37.3"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["2222468"],"award-info":[{"award-number":["2222468"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/lra.2023.3320009","type":"journal-article","created":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T17:43:29Z","timestamp":1695836609000},"page":"7511-7518","source":"Crossref","is-referenced-by-count":0,"title":["Reward Learning With Intractable Normalizing Functions"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0701-163X","authenticated-orcid":false,"given":"Joshua","family":"Hoegerman","sequence":"first","affiliation":[{"name":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8787-5293","authenticated-orcid":false,"given":"Dylan","family":"Losey","sequence":"additional","affiliation":[{"name":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jeon","year":"2020"},{"key":"ref2","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Proc. 20th Int. Joint Conf. Artif. Intell.","author":"Ramachandran","year":"2007"},{"key":"ref3","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. 23rd Nat. Conf. Artif. Intell.","author":"Ziebart","year":"2008"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"ref5","first-page":"362","article-title":"Risk-aware active inverse reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Brown","year":"2018"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1177\/02783649211041652","article-title":"Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences","volume":"41","author":"Byk","year":"2022","journal-title":"Int. J. Robot. Res."},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TRO.2020.2971415"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICRA48506.2021.9562048"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"ref10","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":"ref11","first-page":"182","article-title":"Relative entropy inverse reinforcement learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Boularias","year":"2011"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICRA48506.2021.9560829"},{"key":"ref13","first-page":"6768","article-title":"Inverse reward design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hadfield-Menell","year":"2017"},{"key":"ref14","first-page":"475","article-title":"Continuous inverse optimal control with locally optimal examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine","year":"2012"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1177\/0278364913490324"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1561\/2300000053"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/j.cognition.2009.07.005"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1037\/14396-000"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1080\/00949650902882162"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1214\/15-STS523"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1007\/s11222-014-9521-x"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1080\/01621459.2018.1448824"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1177\/02783649211050958"},{"volume-title":"Artificial Intelligence: A Modern Approach","year":"2022","author":"Russell","key":"ref24"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10254630\/10265168-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10254630\/10265168.pdf?arnumber=10265168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T07:03:06Z","timestamp":1709362986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10265168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":24,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3320009","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}