{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T19:37:18Z","timestamp":1771270638193,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"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":[[2022,8,29]]},"DOI":"10.1109\/ro-man53752.2022.9900563","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:57:30Z","timestamp":1664567850000},"page":"1634-1640","source":"Crossref","is-referenced-by-count":8,"title":["Norm Learning with Reward Models from Instructive and Evaluative Feedback"],"prefix":"10.1109","author":[{"given":"Eric","family":"Rosen","sequence":"first","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric","family":"Hsiung","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivienne Bihe","family":"Chi","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertram F.","family":"Malle","sequence":"additional","affiliation":[{"name":"Brown University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0963721416645512"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"148e","DOI":"10.1111\/cdev.13059","article-title":"From exploration to instruction: Children learn from exploration and tailor their demonstrations to observers’ goals and competence","volume":"90","author":"gweon","year":"2019","journal-title":"Child Development"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889498"},{"key":"ref12","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","author":"jeon","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22362-4_31"},{"key":"ref15","first-page":"184","article-title":"Norms, rewards, and the intentional stance: Comparing machine learning approaches to ethical training","author":"kasenberg","year":"2018"},{"key":"ref16","article-title":"Learning from human-generated reward","author":"knox","year":"2012","journal-title":"PhD dissertation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/40"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref19","article-title":"Convergent actor critic by humans","author":"macglashan","year":"2016","journal-title":"International Conference on Intelligent Robots and Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jecp.2015.09.032"},{"key":"ref4","article-title":"Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferences","author":"biyik","year":"2020","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3404197"},{"key":"ref3","author":"bicchieri","year":"2006","journal-title":"The Grammar of Society The nature and Dynamics of Social Norms"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0748-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199654680.001.0001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0065-2601(08)60330-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889555"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09485-4"},{"key":"ref9","first-page":"159","article-title":"One-shot interaction learning from natural language instruction and demonstration","volume":"6","author":"frasca","year":"2018","journal-title":"Advances in Cognitive Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref20","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume":"70","author":"macglashan","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3849309"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46667-5_1"},{"key":"ref24","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"2000","author":"ng","year":"2000","journal-title":"Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/3849309"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385923"}],"event":{"name":"2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Napoli, Italy","start":{"date-parts":[[2022,8,29]]},"end":{"date-parts":[[2022,9,2]]}},"container-title":["2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9900506\/9900507\/09900563.pdf?arnumber=9900563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:04:50Z","timestamp":1667516690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9900563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ro-man53752.2022.9900563","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]}}}