{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:34:16Z","timestamp":1771612456636,"version":"3.50.1"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246761","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11677-11684","source":"Crossref","is-referenced-by-count":1,"title":["Refined Policy Distillation: From VLA Generalists to RL Experts"],"prefix":"10.1109","author":[{"given":"Tobias","family":"J\u00fclg","sequence":"first","affiliation":[{"name":"University of Technology,Department of Computer Science & Artificial Intelligence,Nuremberg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"University of Technology,Department of Computer Science & Artificial Intelligence,Nuremberg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Walter","sequence":"additional","affiliation":[{"name":"University of Technology,Department of Computer Science & Artificial Intelligence,Nuremberg,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A generalist agent","volume-title":"Proc. of the Int. Conf. on Learning Representations (ICLR)","author":"Reed"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref3","article-title":"RT-2: Vision-language-action models transfer Web knowledge to robotic control","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","author":"Brohan"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref5","article-title":"\u03c00: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"ref6","article-title":"PaLM-e: An embodied multimodal language model","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Driess"},{"key":"ref7","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","author":"Kim"},{"key":"ref8","article-title":"GR-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611331"},{"key":"ref10","article-title":"RLDG: Robotic generalist policy distillation via reinforcement learning","author":"Xu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref12","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","author":"Liang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref14","article-title":"What matters for on-policy deep actor-critic methods? a large-scale study","volume-title":"Proc. of the Int. Conf. on Learning Representations (ICLR)","author":"Andrychowicz"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611477"},{"key":"ref17","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"Proc. of the Conf. on Robot Learning (CoRL)","author":"Doshi"},{"key":"ref18","article-title":"VIMA: Robot manipulation with multimodal prompts","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Jiang"},{"key":"ref19","article-title":"Distilling policy distillation","volume-title":"Proc. of the Int. Conf. on Artificial Intelligence and Statistics (AISTATS)","author":"Czarnecki"},{"key":"ref20","article-title":"Policy distillation","volume-title":"Proc. of the Int. Conf. on Learning Representations (ICLR)","author":"Rusu"},{"key":"ref21","article-title":"Distillation strategies for proximal policy optimization","author":"Green","year":"2019"},{"key":"ref22","article-title":"Reincarnating reinforcement learning: Reusing prior computation to accelerate progress","author":"Agarwal","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Proximal policy distillation","author":"Spigler","year":"2024"},{"key":"ref24","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"Pomerleau","year":"1989","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref26","article-title":"Guided exploration with proximal policy optimization using a single demonstration","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Libardi"},{"key":"ref27","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref28","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Ball"},{"key":"ref29","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the Int. Conf. on Machine Learning (ICML)","author":"Haarnoja"},{"key":"ref30","volume-title":"Reinforcement learning: An introduction.","author":"Sutton","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.021"},{"issue":"274","key":"ref32","article-title":"CleanRL: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246761.pdf?arnumber=11246761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:13:14Z","timestamp":1765519994000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246761","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}