{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:33:21Z","timestamp":1782966801722,"version":"3.54.5"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"publisher","award":["2017\u201305189,2017\u201305102"],"award-info":[{"award-number":["2017\u201305189,2017\u201305102"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001729","name":"Swedish Foundation for Strategic Research","doi-asserted-by":"publisher","award":["SSF FFL18-0199"],"award-info":[{"award-number":["SSF FFL18-0199"]}],"id":[{"id":"10.13039\/501100001729","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,7]]},"DOI":"10.1109\/hri53351.2022.9889604","type":"proceedings-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T19:46:56Z","timestamp":1664480816000},"page":"493-501","source":"Crossref","is-referenced-by-count":12,"title":["Correct Me If I'm Wrong: Using Non-Experts to Repair Reinforcement Learning Policies"],"prefix":"10.1109","author":[{"given":"Sanne","family":"van Waveren","sequence":"first","affiliation":[{"name":"Perception and Learning KTH Royal Institute of Technology,Division of Robotics,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Pek","sequence":"additional","affiliation":[{"name":"Perception and Learning KTH Royal Institute of Technology,Division of Robotics,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jana","family":"Tumova","sequence":"additional","affiliation":[{"name":"Perception and Learning KTH Royal Institute of Technology,Division of Robotics,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iolanda","family":"Leite","sequence":"additional","affiliation":[{"name":"Perception and Learning KTH Royal Institute of Technology,Division of Robotics,Stockholm,Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"2021","journal-title":"Blockly"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.646002"},{"key":"ref33","author":"zaremba","year":"2021","journal-title":"OpenAI codex"},{"key":"ref32","article-title":"Teaching robots new tasks through natural interaction","volume":"26","author":"chai","year":"2017","journal-title":"Interactive Task Learning Agents Robots and Humans Acquiring New Tasks through Natural Interactions Strüngmann Forum Reports"},{"key":"ref31","author":"wang","year":"2020","journal-title":"Too many cooks Coordinating multi-agent col-laboration through inverse planning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3404197"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020227"},{"key":"ref36","first-page":"1146","article-title":"Efficient programming of manipu-lation tasks by demonstration and adaptation","author":"elliott","year":"2017","journal-title":"Proc IEEE Int Symp Robot Human Interactive Commun"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139973"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745110"},{"key":"ref10","article-title":"Policy shaping with human teachers","author":"cederborg","year":"2015","journal-title":"Proc of the Int Joint Conf on Artificial Intelligence"},{"key":"ref40","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":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2200\/S00568ED1V01Y201402AIM028"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2007.4415180"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1007\/978-3-319-02675-6_46","article-title":"Training a robot via human feedback: A case study","author":"knox","year":"2013","journal-title":"Int Conf Social Robot"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.03.015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.00097"},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"2017","journal-title":"Int Conf on Machine Learning"},{"key":"ref28","author":"jansen","year":"2018","journal-title":"Shielded decision-making in MDPs"},{"key":"ref4","author":"shah","year":"2021","journal-title":"The MineRL BASALT competition on learning from human feedback"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref3","author":"hadfield-menell","year":"2017","journal-title":"Inverse reward design"},{"key":"ref6","author":"senft","year":"2021","journal-title":"Task-level authoring for remote robot teleoperation"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76384-8_15"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3242587.3242634"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920910802"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2015.7164385"},{"key":"ref9","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feed-back and guidance with implications for learning performance","volume":"6","author":"thomaz","year":"2006","journal-title":"AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref20","first-page":"1437","article-title":"A comprehensive survey on safe reinforce-ment learning","volume":"16","author":"garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","author":"kress-gazit","year":"2020","journal-title":"Formalizing and guaranteeing human-robot interaction"},{"key":"ref21","first-page":"9797","article-title":"Safe reinforcement learning in constrained Markov decision processes","author":"wachi","year":"2020","journal-title":"Int Conf on Machine Learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993190"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2009.2030225"},{"key":"ref41","first-page":"7498","article-title":"Interactive rein-forcement learning with inaccurate feedback","author":"faulkner","year":"2020","journal-title":"Proc of the IEEE Int Conf on Robotics and Automation"},{"key":"ref23","author":"baier","year":"2008","journal-title":"Principles of Model Checking"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abl7022"},{"key":"ref26","first-page":"452","article-title":"Teaching multiple tasks to an RL agent using LTL","author":"toro icarte","year":"2018","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref43","author":"das","year":"2021","journal-title":"Explainable ai for robot failures Generating explanations that improve user assistance in fault recovery"},{"key":"ref25","author":"hasanbeig","year":"2018","journal-title":"Logically-Constrained Reinforcement Learning"}],"event":{"name":"2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","location":"Sapporo, Japan","start":{"date-parts":[[2022,3,7]]},"end":{"date-parts":[[2022,3,10]]}},"container-title":["2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9889327\/9889305\/09889604.pdf?arnumber=9889604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:52Z","timestamp":1667516752000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/hri53351.2022.9889604","relation":{},"subject":[],"published":{"date-parts":[[2022,3,7]]}}}