{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:36Z","timestamp":1777865376128,"version":"3.51.4"},"reference-count":47,"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\/iccv51701.2025.00959","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10297-10306","source":"Crossref","is-referenced-by-count":0,"title":["Progressor: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement"],"prefix":"10.1109","author":[{"given":"Tewodros W.","family":"Ayalew","sequence":"first","affiliation":[{"name":"University of Chicago,USA"}]},{"given":"Xiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chicago,USA"}]},{"given":"Kevin Yuanbo","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Chicago,USA"}]},{"given":"Tianchong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago,USA"}]},{"given":"Michael","family":"Maire","sequence":"additional","affiliation":[{"name":"University of Chicago,USA"}]},{"given":"Matthew R.","family":"Walter","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161178"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1789"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25733"},{"key":"ref6","article-title":"Scaling egocentric vision: The EPICKITCHENS dataset","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Damen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref8","article-title":"Video prediction models as rewards for reinforcement learning","author":"Escontrela","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref9","article-title":"Contrastive learning as goal-conditioned reinforcement learning","author":"Eysenbach","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"Finn","year":"2016","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2018","journal-title":"arXiv preprint"},{"issue":"59","key":"ref12","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref14","article-title":"Inverse reward design","author":"Hadfield-Menell","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref15","article-title":"Watch and match: Supercharging imitation with regularized optimal transport","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Haldar"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref18","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_27"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66723-8_19"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"InfoGAIL: Interpretable imitation learning from visual demonstrations","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","author":"Jason Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","author":"Jason Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Vision language models are incontext value learners","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Jason Ma"},{"key":"ref27","article-title":"Towards theoretical understanding of inverse reinforcement learning","author":"Maria Metelli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"R3M: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"R3M: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Bin Peng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636557"},{"key":"ref34","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"1995"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8462891"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2018.8462891"},{"key":"ref37","article-title":"Where do rewards come from?","volume-title":"Proceedings of the International Symposium on AI Inspired Biology","author":"Singh"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref39","article-title":"Quest2ROS: An app to facilitate teleoperating robots","volume-title":"Proceedings of the International Workshop on Virtual, Augmented, and Mixed-Reality for Human-Robot Interactions","author":"Welle"},{"key":"ref40","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2016","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610873"},{"key":"ref42","article-title":"Representation matters: Offline pretraining for sequential decision making","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Yarats"},{"key":"ref44","article-title":"MetaWorld: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Yu"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref47","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proceedings of the National Conference on Artificial Intelligence (AAAI)","author":"Ziebart"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445032.pdf?arnumber=11445032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:57Z","timestamp":1777530117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00959","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}