{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:13:59Z","timestamp":1762236839834,"version":"build-2065373602"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"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":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217746","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"857-863","source":"Crossref","is-referenced-by-count":0,"title":["Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations"],"prefix":"10.1109","author":[{"given":"Shijie","family":"Fang","sequence":"first","affiliation":[{"name":"Tufts University School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tufts University School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qidi","family":"Fang","sequence":"additional","affiliation":[{"name":"Tufts University School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reuben M.","family":"Aronson","sequence":"additional","affiliation":[{"name":"Tufts University School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elaine S.","family":"Short","sequence":"additional","affiliation":[{"name":"Tufts University School of Engineering, Computer Science,Medford,Massachusetts,United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"article-title":"Octo: An open-source generalist robot policy","year":"2024","author":"Team","key":"ref2"},{"key":"ref3","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","year":"2023","author":"Padalkar","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN60168.2024.10731359"},{"key":"ref7","first-page":"1732","article-title":"Imitation learning by estimating expertise of demonstrators","volume-title":"International Conference on Machine Learning","author":"Beliaev"},{"article-title":"Behavioral cloning from noisy demonstrations","volume-title":"International Conference on Learning Representations","author":"Sasaki","key":"ref8"},{"issue":"2","key":"ref9","article-title":"Robot learning from demonstration in robotic assembly: A survey","volume-title":"Robotics","volume":"7","author":"Zhu","year":"2018"},{"article-title":"Good better best: Self-motivated imitation learning for noisy demonstrations","year":"2023","author":"Yuan","key":"ref10"},{"article-title":"Learning from suboptimal demonstration via self-supervised reward regression","year":"2020","author":"Chen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3175493"},{"article-title":"Behavioral cloning from noisy demonstrations","volume-title":"International Conference on Learning Representations","author":"Sasaki","key":"ref13"},{"article-title":"Dart: Noise injection for robust imitation learning","year":"2017","author":"Laskey","key":"ref14"},{"article-title":"Robust imitation learning from corrupted demonstrations","year":"2022","author":"Liu","key":"ref15"},{"key":"ref16","first-page":"24 725","article-title":"Discriminator-weighted offline imitation learning from suboptimal demonstrations","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01570-0"},{"key":"ref18","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning","author":"Florence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref22","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Aaai","volume":"8","author":"Ziebart"},{"key":"ref23","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning robust rewards with adversarial inverse reinforcement learning","year":"2017","author":"Fu","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3342559"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.028"},{"key":"ref27","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"International conference on machine learning","author":"Brown"},{"key":"ref28","first-page":"1437","article-title":"Learning to discern: Imitating heterogeneous human demonstrations with preference and representation learning","volume-title":"Conference on Robot Learning","author":"Kuhar"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634925"},{"key":"ref30","first-page":"12 340","article-title":"Confidence-aware imitation learning from demonstrations with varying optimality","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26305"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3418275"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33705"},{"article-title":"Good better best: Self-motivated imitation learning for noisy demonstrations","year":"2023","author":"Yuan","key":"ref35"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2025,8,25]]},"location":"Eindhoven, Netherlands","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217746.pdf?arnumber=11217746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:10:36Z","timestamp":1762236636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217746","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}