{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T09:51:10Z","timestamp":1756461070884,"version":"3.37.3"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002347","name":"German Federal Ministry of Education and Research","doi-asserted-by":"publisher","award":["01IS20045"],"award-info":[{"award-number":["01IS20045"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,28]]},"DOI":"10.1109\/humanoids53995.2022.10000078","type":"proceedings-article","created":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T19:08:26Z","timestamp":1672945706000},"page":"895-902","source":"Crossref","is-referenced-by-count":4,"title":["Learning from Unreliable Human Action Advice in Interactive Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Lisa","family":"Scherf","sequence":"first","affiliation":[{"name":"Interactive AI & Cognitive Models for AI interaction"}]},{"given":"Cigdem","family":"Turan","sequence":"additional","affiliation":[{"name":"Interactive AI & Cognitive Models for AI interaction"}]},{"given":"Dorothea","family":"Koert","sequence":"additional","affiliation":[{"name":"Interactive AI & Cognitive Models for AI interaction"}]}],"member":"263","reference":[{"article-title":"Real-time interactive reinforcement learning for robots","volume-title":"AAAI 2005 Workshop on Human Comprehensible Machine Learning","author":"Thomaz","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3434074.3446361"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00097"},{"key":"ref7","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"Griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"475","article-title":"Reinforcement learning from simultaneous human and mdp reward","author":"Knox","year":"2012","journal-title":"AAMAS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197219"},{"key":"ref10","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume-title":"AAAI","volume":"6","author":"Thomaz"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624972"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00077"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.584075"},{"key":"ref14","article-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback","author":"Arakawa","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280477"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2015.237"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2007.4557293"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/817"},{"key":"ref20","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"},{"key":"ref21","article-title":"Ac-teach: A bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers","author":"Kurenkov","year":"2019","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.37"},{"journal-title":"Should i trust you? incorpo-rating unreliable expert advice in human-agent interaction","author":"Love","key":"ref23"},{"key":"ref24","first-page":"5","article-title":"Combining manual feedback with subse-quent mdp reward signals for reinforcement learning","volume-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume1","volume":"1","author":"Knox"},{"key":"ref25","first-page":"131","article-title":"Learning behaviors with uncertain human feedback","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"He"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/00238309050480010201"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2012.00085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3152832.3152859"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1063\/1.5002892"},{"key":"ref30","first-page":"2529","article-title":"Predicting confusion in infor-mation visualization from eye tracking and interaction data","volume-title":"IJCAI International Joint Conference on Artificial Intelligence","volume":"2016-January","author":"Lalle"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2019.00064"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i18.17998","article-title":"The empathic framework for task learning from implicit human feedback","volume-title":"Conference on Robot Learning","author":"Cui"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395525"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/422"},{"volume-title":"Openface: A general-purpose face recognition library with mobile applications","year":"2016","author":"Amos","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/t27734-000"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704873"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-349-20181-5_26"}],"event":{"name":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2022,11,28]]},"location":"Ginowan, Japan","end":{"date-parts":[[2022,11,30]]}},"container-title":["2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9999736\/9999739\/10000078.pdf?arnumber=10000078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T13:40:04Z","timestamp":1709386804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10000078\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,28]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/humanoids53995.2022.10000078","relation":{},"subject":[],"published":{"date-parts":[[2022,11,28]]}}}