{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:29:20Z","timestamp":1788931760430,"version":"build-2803163510"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iros55552.2023.10341912","type":"proceedings-article","created":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T14:17:55Z","timestamp":1702477075000},"page":"7817-7824","source":"Crossref","is-referenced-by-count":11,"title":["Primitive Skill-Based Robot Learning from Human Evaluative Feedback"],"prefix":"10.1109","author":[{"given":"Ayano","family":"Hiranaka","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjune","family":"Hwang","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharon","family":"Lee","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruohan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/884"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006254"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref6","first-page":"738","article-title":"A dual representation framework for robot learning with human guidance","volume-title":"Conference on Robot Learning","author":"Zhang","year":"2023"},{"key":"ref7","author":"Zhu","year":"2020","journal-title":"robosuite: A modular simulation framework and benchmark for robot learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref9","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume-title":"Proceedings of the 21st National Conference on Artificial Intelligence -","volume":"1","author":"Thomaz","year":"2006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09459-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16952-6_49"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196566"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref17","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proceedings of the 34th International Conference on Machine Learning-Volume","volume":"70","author":"James","year":"2017"},{"key":"ref18","author":"Arumugam","year":"2019","journal-title":"Deep reinforcement learning from policy-dependent human feedback"},{"key":"ref19","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","volume-title":"Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems","author":"Bradley Knox","year":"2010"},{"key":"ref20","first-page":"475","article-title":"Reinforcement learning from simultaneous human and mdp reward","volume-title":"Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems","volume":"1","author":"Bradley Knox","year":"2012"},{"key":"ref21","author":"Arakawa","year":"2018","journal-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100940"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2016.7745140"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981440"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561548"},{"key":"ref27","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2022"},{"key":"ref28","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560841"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3186635"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3308061"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160220"},{"key":"ref33","first-page":"80","article-title":"Behavior-lk: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation","volume-title":"Conference on Robot Learning","author":"Li","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943079"},{"key":"ref35","first-page":"1930","article-title":"Logic-geometric programming: An optimization-based approach to combined task and motion planning","author":"Toussaint","year":"2015","journal-title":"IJCAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref38","first-page":"1199","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Conference on Robot Learning","author":"Zhu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja","year":"2018"},{"key":"ref41","author":"Haarnoja","year":"2018","journal-title":"Soft actor-critic algorithms and applications"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2012.05.028"},{"key":"ref44","article-title":"Prioritized experience replay","volume-title":"4th International Conference on Learning Representations, ICLR","author":"Schaul","year":"2016"}],"event":{"name":"2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Detroit, MI, USA","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,5]]}},"container-title":["2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10341341\/10341342\/10341912.pdf?arnumber=10341912","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:15:45Z","timestamp":1703013345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10341912\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros55552.2023.10341912","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}