{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T04:15:27Z","timestamp":1772338527271,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460854","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:28:03Z","timestamp":1537568883000},"page":"6907-6914","source":"Crossref","is-referenced-by-count":29,"title":["Active Reward Learning from Critiques"],"prefix":"10.1109","author":[{"given":"Yuchen","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Niekum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Active preference-based learning of reward functions","author":"dragan","year":"2017","journal-title":"Robotics Science and Systems (RSS)"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7690","article-title":"Reinforcement learning via practice and critique advice","author":"judah","year":"2010","journal-title":"AAAI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2451176.2451201"},{"key":"ref13","author":"kulick","year":"2014","journal-title":"The Advantage of Cross Entropy over Entropy in Iterative Information Gathering"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref15","first-page":"31","article-title":"Active learning for reward estimation in inverse reinforcement learning","author":"lopes","year":"2009","journal-title":"Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/b10905-6"},{"key":"ref17","author":"pazis","year":"2011","journal-title":"Non-parametric approximate linear programming for mdps"},{"key":"ref18","first-page":"1","article-title":"Bayesian inverse reinforcement learning","volume":"51","author":"ramachandran","year":"2007","journal-title":"Urbana"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228725"},{"key":"ref6","article-title":"Comprehensive survey on distance\/similarity measures between probability density functions","volume":"1","author":"cha","year":"2007","journal-title":"city"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"ref8","author":"christiano","year":"2017","journal-title":"Deep reinforcement learning from human preferences"},{"key":"ref7","first-page":"1989","article-title":"Map inference for bayesian inverse reinforcement learning","author":"choi","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref2","author":"anzai","year":"2012","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","first-page":"1287","article-title":"Comparing action-query strategies in semi-autonomous agents","volume":"3","author":"cohn","year":"2011","journal-title":"The 10th International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2016060"},{"key":"ref22","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref21","first-page":"2198","article-title":"Robust bayesian inverse reinforcement learning with sparse behavior noise","author":"zheng","year":"2014","journal-title":"AAAI"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08460854.pdf?arnumber=8460854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T09:07:12Z","timestamp":1693904832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460854","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}