{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:46:55Z","timestamp":1777567615523,"version":"3.51.4"},"reference-count":39,"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\/icra55743.2025.11128127","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"12010-12016","source":"Crossref","is-referenced-by-count":3,"title":["FDPP: Fine-Tune Diffusion Policy with Human Preference"],"prefix":"10.1109","author":[{"given":"Yuxin","family":"Chen","sequence":"first","affiliation":[{"name":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devesh K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[{"name":"UC Berkeley,Mechanical Systems Control Lab,Berkeley,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Romeres","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","volume-title":"7 th Annual Conference on Robot Learning","author":"Wang"},{"key":"ref2","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning. PMLR","author":"Ze"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.067"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning. PMLR","author":"Sohl-Dickstein"},{"key":"ref10","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"arXiv preprint","author":"Janner","year":"2022"},{"key":"ref12","article-title":"Diffusionreinforcement learning hierarchical motion planning in adversarial multi-agent games","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"issue":"2","key":"ref13","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref14","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.053"},{"key":"ref16","first-page":"519","article-title":"Batch active preference-based learning of reward functions","volume-title":"Conference on robot learning. PMLR","author":"Biyik"},{"issue":"136","key":"ref17","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref18","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"International conference on machine learning. PMLR","author":"Brown"},{"key":"ref19","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Time-efficient reward learning via visually assisted cluster ranking","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Benchmarks and algorithms for offline preference-based reward learning","author":"Shin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"What matters to you? towards visual representation alignment for robot learning","author":"Tian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Optimizing ddpm sampling with shortcut finetuning","author":"Fan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref25","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Diffusion policy policy optimization","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"International conference on machine learning. Pmlr","author":"Silver"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref31","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Rl-vlm-f: Reinforcement learning from vision language foundation model feedback","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref35","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning. PMLR","author":"Florence"},{"key":"ref36","article-title":"Mimicgen: A data generation system for scalable robot learning using human demonstrations","author":"Mandlekar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"}],"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\/11128127.pdf?arnumber=11128127","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:52Z","timestamp":1756879612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128127\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128127","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}