{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T04:15:28Z","timestamp":1772338528880,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197219","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"7498-7504","source":"Crossref","is-referenced-by-count":9,"title":["Interactive Reinforcement Learning with Inaccurate Feedback"],"prefix":"10.1109","author":[{"given":"Taylor A.","family":"Kessler Faulkner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elaine","family":"Schaertl Short","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea L.","family":"Thomaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref11","first-page":"447","article-title":"Exploration from demonstration for interactive reinforcement learning","author":"subramanian","year":"2016","journal-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems"},{"key":"ref12","article-title":"Explore, exploit or listen: Combining human feedback and policy model to speed up deep reinforcement learning in 3d worlds","author":"lin","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2015.237"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2007.4557293"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref16","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"ref17","article-title":"Models of delayed reinforcement learning","author":"watkins","year":"1989","journal-title":"PhD thesis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10010","article-title":"Learning the preferences of ignorant, inconsistent agents","author":"evans","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"key":"ref3","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","author":"knox","year":"2010","journal-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems Volume 1-Volume 1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0161-z"},{"key":"ref5","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume":"97","author":"brown","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.37"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8979","article-title":"Robust bayesian inverse reinforcement learning with sparse behavior noise","author":"zheng","year":"2014","journal-title":"Twenty-Eighth AAAI Conference on Artificial Intelligence"},{"key":"ref2","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/656"},{"key":"ref9","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"ve?er\u00edk","year":"2017","journal-title":"arXiv preprint arXiv 1707 08817"},{"key":"ref20","volume":"2","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref22","article-title":"An object recognition and pose estimation library for intelligent industrial automation","author":"allevato","year":"2016","journal-title":"Master’s thesis"},{"key":"ref21","article-title":"Policy shaping with human teachers","author":"cederborg","year":"2015","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197219.pdf?arnumber=9197219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:58:27Z","timestamp":1668779907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197219","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}