{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:18Z","timestamp":1766061618781,"version":"3.48.0"},"reference-count":46,"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\/iros60139.2025.11246124","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11343-11350","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Policy Idling for Dexterous Manipulation"],"prefix":"10.1109","author":[{"given":"Annie S.","family":"Chen","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philemon","family":"Brakel","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonia","family":"Bronars","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annie","family":"Xie","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandy","family":"Huang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Groth","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Bauza","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Wulfmeier","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Heess","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dushyant","family":"Rao","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"article-title":"Causal imitation learning under temporally correlated noise","volume-title":"ICML","author":"Swamy","key":"ref3"},{"article-title":"Bidirectional decoding: Improving action chunking via closed-loop resampling","year":"2024","author":"Liu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.046217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-8914(40)90098-2"},{"article-title":"So you think you can scale up autonomous robot data collection?","year":"2024","author":"Mirchandani","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00043"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00187"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref12","article-title":"Reverse curriculum generation for reinforcement learning","author":"Florensa","year":"2017","journal-title":"CoRL"},{"article-title":"To err is robotic: Rapid value-based trial-and-error during deployment","year":"2024","author":"Du","key":"ref13"},{"article-title":"Steering your generalists: Improving robotic foundation models via value guidance","year":"2024","author":"Nakamoto","key":"ref14"},{"key":"ref15","first-page":"14 784","article-title":"You only live once: Single-life reinforcement learning","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981315"},{"article-title":"Robo-cat: A self-improving foundation agent for robotic manipulation","year":"2023","author":"Bousmalis","key":"ref17"},{"article-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","year":"2024","author":"Ahn","key":"ref18"},{"key":"ref19","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"AISTATS","author":"Ross"},{"key":"ref20","article-title":"Dart: Noise injection for robust imitation learning","author":"Laskey","year":"2017","journal-title":"CoRL"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"article-title":"Thriftydagger: Budget-aware novelty and risk gating for interactive imitation learning","year":"2021","author":"Hoque","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802498"},{"article-title":"Awac: Accelerating online reinforcement learning with offline datasets","year":"2020","author":"Nair","key":"ref24"},{"key":"ref25","article-title":"Offline-to-online reinforcement learning via balanced replay and pessimistic q-ensemble","author":"Lee","year":"2022","journal-title":"CoRL"},{"key":"ref26","article-title":"Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning","volume":"36","author":"Nakamoto","year":"2024","journal-title":"NeurIPS"},{"article-title":"Idql: Implicit q-learning as an actor-critic method with diffusion policies","year":"2023","author":"Hansen-Estruch","key":"ref27"},{"article-title":"Coarse-to-fine q-network with action sequence for data-efficient robot learning","year":"2025","author":"Seo","key":"ref28"},{"article-title":"Diffusion policy policy optimization","year":"2024","author":"Ren","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref31","article-title":"Deep exploration via bootstrapped dqn","author":"Osband","year":"2016","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s12064-011-0142-z"},{"article-title":"Large-scale study of curiosity-driven learning","year":"2018","author":"Burda","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.11.008"},{"key":"ref36","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","author":"Brown","year":"2020","journal-title":"CoRL"},{"article-title":"Emergence of in-context reinforcement learning from noise distillation","year":"2023","author":"Zisman","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561662"},{"article-title":"Ccil: Continuity-based data augmentation for corrective imitation learning","year":"2023","author":"Ke","key":"ref39"},{"key":"ref40","article-title":"Collect & infer-a fresh look at data-efficient reinforcement learning","author":"Riedmiller","year":"2022","journal-title":"CoRL"},{"article-title":"Preference optimization as probabilistic inference","year":"2024","author":"Abdolmaleki","key":"ref41"},{"article-title":"Offline actor-critic reinforcement learning scales to large models","year":"2024","author":"Springenberg","key":"ref42"},{"article-title":"Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","year":"2025","author":"Tschannen","key":"ref43"},{"article-title":"Aloha unleashed: A simple recipe for robot dexterity","year":"2024","author":"Zhao","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127813"},{"article-title":"Exploration by random network distillation","year":"2018","author":"Burda","key":"ref46"}],"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\/11246124.pdf?arnumber=11246124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:35:50Z","timestamp":1766061350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246124","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}