{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:55Z","timestamp":1765519855348,"version":"3.48.0"},"reference-count":38,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11245841","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9792-9799","source":"Crossref","is-referenced-by-count":0,"title":["SIME: Enhancing Policy Self-Improvement with Modal-level Exploration"],"prefix":"10.1109","author":[{"given":"Yang","family":"Jin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Lv","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenye","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Lu","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref1"},{"article-title":"From imitation to refinement\u2013 residual rl for precise visual assembly","volume-title":"CoRL 2024 Workshop on Mastering Robot Manipulation in a World of Abundant Data","author":"Lien Ankile","key":"ref2"},{"article-title":"Robocat: A self-improving generalist agent for robotic manipulation","year":"2023","author":"Bousmalis","key":"ref3"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128787"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"article-title":"AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons","year":"2025","author":"Fang","key":"ref9"},{"key":"ref10","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on Robot Learning","author":"Florence"},{"key":"ref11","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref12","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Transic: Sim-to-real policy transfer by learning from online correction","year":"2024","author":"Jiang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Offline reinforcement learning with implicit q-learning","year":"2021","author":"Kostrikov","key":"ref18"},{"key":"ref19","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":"ref20","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273901"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.ads5033"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127637"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241284653"},{"article-title":"What matters in learning from offline human demonstrations for robot manipulation","year":"2021","author":"Mandlekar","key":"ref26"},{"article-title":"So You Think You Can Scale Up Autonomous Robot Data Collection?","volume-title":"In: Conference on Robot Learning","author":"Mirchandani","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","year":"2019","author":"Bin Peng","key":"ref29"},{"article-title":"CADS: Unleashing the diversity of diffusion models through condition-annealed sampling","year":"2023","author":"Sadat","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref32","first-page":"22955","article-title":"Behavior transformers: Cloning k modes with one stone","volume":"35","author":"Muhammad Shafiullah","year":"2022","journal-title":"Advances in neural information processing systems"},{"article-title":"Residual policy learning","year":"2018","author":"Silver","key":"ref33"},{"article-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"key":"ref36","article-title":"Exponentially weighted imitation learning for batched historical data","volume":"31","author":"Wang","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","year":"2024","author":"Yuan","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","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\/11245841.pdf?arnumber=11245841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:08:27Z","timestamp":1765519707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11245841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11245841","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}