{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:04:16Z","timestamp":1762254256420,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,7]]},"DOI":"10.1109\/hri53351.2022.9889498","type":"proceedings-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T19:46:56Z","timestamp":1664480816000},"page":"807-811","source":"Crossref","is-referenced-by-count":6,"title":["Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback"],"prefix":"10.1109","author":[{"given":"Eric","family":"Hsiung","sequence":"first","affiliation":[{"name":"Brown University,Providence,RI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Rosen","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivienne Bihe","family":"Chi","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertram F.","family":"Malle","sequence":"additional","affiliation":[{"name":"Brown University,Providence,RI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017749"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09485-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/374"},{"journal-title":"Learning from Human-generated Reward","year":"2012","author":"knox","key":"ref13"},{"key":"ref14","article-title":"Convergent actor critic by humans","author":"macglashan","year":"2016","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref15","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume":"70","author":"macglashan","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3849309"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/cdev.13443"},{"key":"ref3","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","author":"ramachandran","year":"2007","journal-title":"IJCAI 2007 Proceedings of the 20th International Joint Conference on Artificial Intelligence"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/87567555.1994.9926845"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X14000090"},{"key":"ref8","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","volume":"abs 2006 14091","author":"biyik","year":"2020","journal-title":"CoRR"},{"key":"ref1","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","author":"jeon","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020 December 6–12 2020 virtual"},{"key":"ref9","article-title":"Quantifying differences in reward functions","author":"gleave","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021 Virtual Event Austria May 3–7 2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889555"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0007362"},{"key":"ref21","first-page":"5916","article-title":"Revisiting the softmax bellman operator: New benefits and new perspective","volume":"97","author":"song","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"journal-title":"Brain function and adaptive systems - A heterostatic theory","year":"1972","author":"klopf","key":"ref24"},{"key":"ref23","volume":"abs 1902 6865","author":"fedus","year":"2019","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17200"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"}],"event":{"name":"2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","start":{"date-parts":[[2022,3,7]]},"location":"Sapporo, Japan","end":{"date-parts":[[2022,3,10]]}},"container-title":["2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9889327\/9889305\/09889498.pdf?arnumber=9889498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:33Z","timestamp":1667516733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/hri53351.2022.9889498","relation":{},"subject":[],"published":{"date-parts":[[2022,3,7]]}}}