{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:59:52Z","timestamp":1777654792400,"version":"3.51.4"},"reference-count":52,"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\/icra55743.2025.11128278","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"9574-9581","source":"Crossref","is-referenced-by-count":1,"title":["TREND: Tri-Teaching for Robust Preference-based Reinforcement Learning with Demonstrations"],"prefix":"10.1109","author":[{"given":"Shuaiyi","family":"Huang","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Mara","family":"Levy","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Anubhav","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Daniel","family":"Ekpo","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Ruijie","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]},{"given":"Abhinav","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Lee","year":"2021"},{"key":"ref2","article-title":"Surf: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Park"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2017.XIII.053","article-title":"Active preference-based learning of reward functions","volume-title":"Robotics: Science and Systems","author":"Sadigh","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611088"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"ref6","article-title":"A bayesian approach for policy learning from trajectory preference queries","volume":"25","author":"Wilson","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10269"},{"key":"ref8","article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"B-pref: Benchmarking preference-based reinforcement learning","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track","author":"Lee"},{"key":"ref10","article-title":"Rime: Robust preference-based reinforcement learning with noisy preferences","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","author":"Cheng"},{"key":"ref11","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robot Learning (CoRL)","author":"Yu"},{"key":"ref12","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"519","article-title":"Batch active preference-based learning of reward functions","volume-title":"Conference on robot learning","author":"Biyik"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.041"},{"key":"ref16","volume-title":"Reward uncertainty for exploration in preference-based reinforcement learning","author":"Liang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref20","article-title":"Training deep neural-networks using a noise adaptation layer","volume-title":"International conference on learning representations","author":"Goldberger"},{"key":"ref21","first-page":"6448","article-title":"Does label smoothing mitigate label noise?","volume-title":"International Conference on Machine Learning","author":"Lukasik"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/586"},{"key":"ref23","article-title":"Tracevla: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00273"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00274"},{"key":"ref26","article-title":"Lmpriors: Pre-trained language models as task-specific priors","author":"Choi","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"8657","article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"International Conference on Machine Learning","author":"Du"},{"key":"ref28","article-title":"Vision-language models are zero-shot reward models for reinforcement learning","author":"Rocamonde","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.145"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_16"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60633-6_8"},{"key":"ref32","volume-title":"Motif: Intrinsic motivation from artificial intelligence feedback","author":"Klissarov","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00594"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802264"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA55743.2025.11128755","article-title":"P3-po: Prescriptive point priors for visuo-spatial generalization of robot policies","volume-title":"International Conference on Robotics and Automaction(ICRA)","author":"Levy"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.493"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01486"},{"key":"ref39","article-title":"PRISE: LLM-style sequence compression for learning temporal action abstractions in control","volume-title":"Forty-first International Conference on Machine Learning","author":"Zheng"},{"key":"ref40","article-title":"Premier-taco is a few-shot policy learner: Pretraining multitask representation via temporal action-driven contrastive loss","volume-title":"Forty-first International Conference on Machine Learning","author":"Zheng","year":"2024"},{"key":"ref41","article-title":"TACO: Temporal latent action-driven contrastive loss for visual reinforcement learning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Zheng"},{"key":"ref42","volume-title":"Text2reward: Reward shaping with language models for reinforcement learning","author":"Xie","year":"2024"},{"key":"ref43","article-title":"Reward design with language models","author":"Kwon","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref45","first-page":"22270","article-title":"Meta-reward-net: Implicitly differentiable reward learning for preference-based reinforcement learning","volume":"35","author":"Liu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"Preference transformer: Modeling human preferences using transformers for rl","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111400"},{"key":"ref49","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/01966324.2003.10737616"},{"key":"ref51","first-page":"1861","article-title":"Soft actorcritic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"80","author":"Haarnoja"},{"key":"ref52","volume-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2024"}],"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\/11128278.pdf?arnumber=11128278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:34:04Z","timestamp":1756881244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128278","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}