{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:59:37Z","timestamp":1773521977896,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128018","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15673-15679","source":"Crossref","is-referenced-by-count":3,"title":["MILE: Model-Based Intervention Learning"],"prefix":"10.1109","author":[{"given":"Yigit","family":"Korkmaz","sequence":"first","affiliation":[{"name":"University of Southern California,Thomas Lord Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erdem","family":"B\u0131y\u0131k","sequence":"additional","affiliation":[{"name":"University of Southern California,Thomas Lord Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Kalashnikov","year":"2018"},{"issue":"1","key":"ref2","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref3","article-title":"Training language models to follow instructions with human feedback","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ouyang","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","article-title":"Efficient reductions for imitation learning","volume-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics","author":"Ross","year":"2010"},{"key":"ref6","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","author":"Ross","year":"2011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"ref9","article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Hoque","year":"2022"},{"key":"ref10","article-title":"Fleet-dagger: Interactive robot fleet learning with scalable human supervision","volume-title":"Conference on Robot Learning (CoRL)","author":"Hoque","year":"2023"},{"key":"ref11","volume-title":"Human-interactive robot learning: Definition, challenges, and recommendations","author":"Baraka","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.005"},{"key":"ref13","article-title":"Human-in-the-loop imitation learning using remote teleoperation","author":"Mandlekar","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.055"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/2300000072"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref17","article-title":"Generative adversarial imitation learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2016"},{"key":"ref18","article-title":"Dart: Noise injection for robust imitation learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Laskey","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref20","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Pomerleau","year":"1988"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160439"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3145516"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref24","article-title":"Efficient online reinforcement learning with offline data","volume-title":"International Conference on Machine Learning (ICML)","author":"Ball","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref26","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Xie","year":"2021"},{"key":"ref27","article-title":"Efficient learning of safe driving policy via human-ai copilot optimization","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Rlif: Interactive imitation learning as reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Luo","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974241"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2003.1174284"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121249"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fnrgo.2023.1171403"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-020-00703-3"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1145\/3171221.3171264","article-title":"Planning with trust for human-robot collaboration","volume-title":"International Conference on Human-robot Interaction (HRI)","author":"Chen","year":"2018"},{"key":"ref35","article-title":"Trial without error: Towards safe reinforcement learning via human intervention","volume-title":"International Conference on Autonomous Agents and Multiagent Systems","author":"Saunders","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1126\/science.79.2037.38"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913490324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2015.xi.032"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1145\/3319502.3374832","article-title":"When humans aren\u2019t optimal: Robots that collaborate with risk-aware humans","volume-title":"International Conference on Human-Robot Interaction (HRI)","author":"Kwon","year":"2020"},{"key":"ref40","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ziebart","year":"2008"},{"key":"ref41","article-title":"The boltzmann policy distribution: Accounting for systematic suboptimality in human models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Laidlaw","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.31096\/wua9999-wp_0551_box_5"},{"key":"ref43","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu","year":"2019"},{"key":"ref44","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Sontakke","year":"2023"},{"key":"ref45","article-title":"Transic: Sim-to-real policy transfer by learning from online correction","volume-title":"Conference on Robot Learning (CoRL)","author":"Jiang","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801523"},{"key":"ref47","article-title":"Trajectory improvement and reward learning from comparative language feedback","volume-title":"Conference on Robot Learning (CoRL)","author":"Yang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.025"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128018.pdf?arnumber=11128018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:46:17Z","timestamp":1756881977000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128018","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}