{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:41:12Z","timestamp":1766061672934,"version":"3.48.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247163","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7917-7924","source":"Crossref","is-referenced-by-count":0,"title":["CueLearner: Bootstrapping and local policy adaptation from relative feedback"],"prefix":"10.1109","author":[{"given":"Giulio","family":"Schiavi","sequence":"first","affiliation":[{"name":"ETH Zurich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei","family":"Cramariuc","sequence":"additional","affiliation":[{"name":"ETH Zurich,Robotics Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Ott","sequence":"additional","affiliation":[{"name":"ETH Zurich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[{"name":"ETH Zurich,Autonomous Systems Lab,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref3","article-title":"Action advising with advice imitation in deep reinforcement learning","volume-title":"Adaptive Agents and Multi-Agent Systems","author":"Ilhan","year":"2021"},{"article-title":"Dqn-tamer: Human-in-the-loop reinforcement learning with intractable feedback","year":"2018","author":"Arakawa","key":"ref4"},{"key":"ref5","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","volume":"10","author":"Knox","year":"2010","journal-title":"AAMAS"},{"article-title":"PEBBLE: feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","year":"2021","author":"Lee","key":"ref6"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-33950-0_31","article-title":"Interactive learning with corrective feedback for policies based on deep neural networks","volume-title":"International Symposium on Experimental Robotics","author":"P\u00e9rez-Dattari"},{"key":"ref8","first-page":"1560","article-title":"Reinforcement learning of motor skills using policy search and human corrective advice","volume-title":"The International Journal of Robotics Research","volume":"38","author":"Celemin","year":"2019"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1145\/3568162.3578623","article-title":"No, to the right: Online language corrections for robotic manipulation via shared autonomy","volume-title":"Proceedings of the 2023 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Cui"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0839-z"},{"key":"ref12","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of the Seventeenth International Conference on Machine Learning","author":"Ng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref14","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proceedings of the 34th International Conference on Machine Learning","volume":"70","author":"MacGlashan"},{"key":"ref15","article-title":"Deep reinforcement learning from human preferences","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Christiano","year":"2017"},{"article-title":"Few-shot preference learning for human-in-the-loop rl","volume-title":"Conference on Robot Learning","author":"Hejna","key":"ref16"},{"key":"ref17","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in sparse reward environments","volume-title":"Adaptive Agents and Multi-Agent Systems","author":"Goecks","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2017.8329809"},{"article-title":"Modem: Accelerating visual model-based reinforcement learning with demonstrations","year":"2022","author":"Hansen","key":"ref19"},{"article-title":"Interactive robot learning from verbal correction","year":"2023","author":"Liu","key":"ref20"},{"key":"ref21","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics","volume":"15","author":"Ross"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/70.508439"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247163.pdf?arnumber=11247163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:50Z","timestamp":1766061470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247163","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}