{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:07:05Z","timestamp":1779944825950,"version":"3.53.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Singapore National Robotics Programme through Research Project","award":["DS-RFM M25N4N2009"],"award-info":[{"award-number":["DS-RFM M25N4N2009"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/lra.2026.3693577","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:59:35Z","timestamp":1778788775000},"page":"8084-8091","source":"Crossref","is-referenced-by-count":0,"title":["E2HiL: Entropy-Guided Sample Selection for Efficient Real-World Human-in-the-Loop Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5975-0394","authenticated-orcid":false,"given":"Haoyuan","family":"Deng","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudong","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9974-6576","authenticated-orcid":false,"given":"Yuanjiang","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyang","family":"Du","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianzhun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4827-6017","authenticated-orcid":false,"given":"Zhenyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9225-8495","authenticated-orcid":false,"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Empowering embodied manipulation: A bimanual-mobile robot manipulation dataset for household tasks","author":"Zhang","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ads5033"},{"key":"ref3","article-title":"A survey on reinforcement learning of vision-language-action models for robotic manipulation","author":"Deng","year":"2025","journal-title":"Authorea Preprints"},{"key":"ref4","article-title":"VLA-RL: Towards masterful and general robotic manipulation with scalable reinforcement learning","author":"Lu","year":"2025"},{"key":"ref5","article-title":"NORA-1.5: A vision-language-action model trained using world model-and action-based preference rewards","author":"Hung","year":"2025"},{"key":"ref6","first-page":"1","article-title":"VLA-reasoner: Empowering vision-language-action models with reasoning via online Monte Carlo tree search","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Guo","year":"2026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3295236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3400189"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/17298814211007305"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.015"},{"key":"ref11","article-title":"SPARQ: Selective progress-aware resource querying","volume-title":"Proc. CoRL Workshop Resource-Rational Robot Learn.","author":"Muraleedharan","year":"2025"},{"key":"ref12","article-title":"The entropy mechanism of reinforcement learning for reasoning language models","author":"Cui","year":"2025"},{"key":"ref13","article-title":"SimpleVLA-RL: Scaling VLA training via reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35095"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-021-10006-9"},{"key":"ref17","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Proc. Conf. Robot Learn.","author":"Clavera","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/02783649221083331"},{"key":"ref20","article-title":"RL-100: Performant robotic manipulation with real-world reinforcement learning","author":"Lei","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2024.2408593"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3497992"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561384"},{"key":"ref27","article-title":"World models increase autonomy in reinforcement learning","volume-title":"Trans. Mach. Learn. Res.","author":"Yang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-022-00942-6"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Mach. Learn. Res.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref30","first-page":"1","article-title":"Maximum a posteriori policy optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Abdolmaleki","year":"2018"},{"key":"ref31","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ball","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i36.40290"},{"key":"ref33","first-page":"34161","article-title":"Fast rates for maximum entropy exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tiapkin","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.432"},{"key":"ref35","first-page":"1","article-title":"Maximum entropy RL (provably) solves some robust RL problems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2719"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11520247.pdf?arnumber=11520247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T04:50:52Z","timestamp":1779943852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11520247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":37,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3693577","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}