{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:09:21Z","timestamp":1762254561932,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141612835,N000141612785"],"award-info":[{"award-number":["N000141612835,N000141612785"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1564080,1724157"],"award-info":[{"award-number":["1564080,1724157"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161105","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"9414-9420","source":"Crossref","is-referenced-by-count":3,"title":["Using Learning Curve Predictions to Learn from Incorrect Feedback"],"prefix":"10.1109","author":[{"given":"Taylor A. Kessler","family":"Faulkner","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea L.","family":"Thomaz","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2067","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","author":"saunders","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref12","first-page":"arxiv-1709","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 e-prints"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525837"},{"key":"ref11","first-page":"16","article-title":"Interaction algorithm effect on human experience with reinforcement learning","volume":"7","year":"2018","journal-title":"ACM Transactions on Human-Robot Interaction (THRI)"},{"key":"ref10","first-page":"720","article-title":"Newtonian action advice: Integrating human verbal instruction with reinforcement learning","author":"krening","year":"0","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"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":"10.1109\/THMS.2019.2912447"},{"key":"ref17","first-page":"arxiv-1709","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"ArXiv e-prints"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref19","article-title":"Ac-teach: A bayesian actor-critic method for policy learning with an ensemble of suboptimal teachers","author":"kurenkov","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref18","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8979"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0161-z"},{"journal-title":"Models of Delayed Reinforcement Learning","year":"1989","author":"watkins","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.37"},{"key":"ref22","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Interactive reinforcement learning with inaccurate feedback","author":"faulkner","year":"0","journal-title":"2020 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref28","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","article-title":"Policy shaping with human teachers","author":"cederborg","year":"0","journal-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence"},{"key":"ref8","first-page":"447","article-title":"Exploration from demonstration for interactive reinforcement learning","author":"subramanian","year":"0","journal-title":"Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems"},{"key":"ref7","first-page":"475","article-title":"Reinforcement learning from simultaneous human and mdp reward","author":"knox","year":"0","journal-title":"Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1"},{"key":"ref9","article-title":"Spare: an efficient way to combine reinforcement learning and supervised autonomy","author":"senft","year":"0","journal-title":"NIPS Workshop - The Future of Interactive Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06375-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref5"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2023,5,29]]},"location":"London, United Kingdom","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161105.pdf?arnumber=10161105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:38:01Z","timestamp":1690220281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161105","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}