{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T03:07:47Z","timestamp":1789787267275,"version":"4.0.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015599","name":"Toyota Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015599","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610421","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T13:51:05Z","timestamp":1723125065000},"page":"4804-4811","source":"Crossref","is-referenced-by-count":15,"title":["Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jingyun","family":"Yang","sequence":"first","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max Sobol","family":"Mark","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandon","family":"Vu","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Archit","family":"Sharma","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chelsea","family":"Finn","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.019"},{"key":"ref7","first-page":"1652","article-title":"Don\u2019t start from scratch: Leveraging prior data to automate robotic reinforcement learning","volume-title":"Conference on Robot Learning","author":"Walke"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref10","first-page":"642","article-title":"High acceleration reinforcement learning for real-world juggling with binary rewards","volume-title":"Conference on Robot Learning","author":"Ploeger"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref12","first-page":"308","article-title":"Fully autonomous real-world reinforcement learning with applications to mobile manipulation","volume-title":"Conference on Robot Learning","author":"Sun"},{"key":"ref13","article-title":"Self-improving robots: End-to-end autonomous visuomotor reinforcement learning","author":"Sharma","year":"2023"},{"key":"ref14","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2021"},{"key":"ref15","article-title":"Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning","author":"Nakamoto","year":"2023"},{"key":"ref16","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022"},{"key":"ref17","article-title":"A state-distribution matching approach to non-episodic reinforcement learning","author":"Sharma","year":"2022"},{"key":"ref18","article-title":"Liv: Language-image representations and rewards for robotic control","author":"Ma","year":"2023"},{"key":"ref19","article-title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets","author":"Ebert","year":"2021"},{"key":"ref20","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref21","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019"},{"key":"ref22","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref23","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"1719","article-title":"Plas: Latent action space for offline reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zhou"},{"key":"ref26","article-title":"Accelerating online reinforcement learning with offline datasets","author":"Ashvin","year":"2020","journal-title":"CoRR, vol. abs\/2006.09359"},{"key":"ref27","first-page":"1154","article-title":"Offline reinforcement learning from images with latent space models","volume-title":"Learning for Dynamics and Control","author":"Rafailov","year":"2021"},{"key":"ref28","first-page":"1711","article-title":"Mildly conservative q-learning for offline reinforcement learning","volume":"35","author":"Lyu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Improving td3-bc: Relaxed policy constraint for offline learning and stable online fine-tuning","author":"Beeson","year":"2022"},{"key":"ref30","first-page":"31278","article-title":"Supported policy optimization for offline reinforcement learning","volume":"35","author":"Wu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","first-page":"1702","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","volume-title":"Conference on Robot Learning","author":"Lee"},{"key":"ref32","article-title":"Fine-tuning offline policies with optimistic action selection","volume-title":"Deep Reinforcement Learning Workshop NeurIPS 2022","author":"Mark"},{"key":"ref33","article-title":"Reset-free lifelong learning with skill-space planning","author":"Lu","year":"2020"},{"key":"ref34","article-title":"Learning to walk in the real world with minimal human effort","author":"Ha","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161447"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161493"},{"key":"ref37","article-title":"Leave no trace: Learning to reset for safe and autonomous reinforcement learning","author":"Eysenbach","year":"2017"},{"key":"ref38","article-title":"The ingredients of real-world robotic reinforcement learning","author":"Zhu","year":"2020"},{"key":"ref39","first-page":"18474","article-title":"Autonomous reinforcement learning via subgoal curricula","volume":"34","author":"Sharma","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"Ng","year":"2000","journal-title":"Icml"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref42","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Aaai","volume":"8","author":"Ziebart","year":"2008"},{"key":"ref43","first-page":"2760","article-title":"Model-free imitation learning with policy optimization","volume-title":"International conference on machine learning","author":"Ho"},{"key":"ref44","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref45","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref46","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"Fu","year":"2017"},{"key":"ref47","first-page":"8547","article-title":"Variational inverse control with events: A general framework for data-driven reward definition","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Fu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref49","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref51","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref52","article-title":"Vision-language models as success detectors","author":"Du","year":"2023"},{"key":"ref53","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref54","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Walke","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610421.pdf?arnumber=10610421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:50:42Z","timestamp":1772484642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610421","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}