{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T02:36:04Z","timestamp":1730255764076,"version":"3.28.0"},"reference-count":44,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icra57147.2024.10611076","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"9220-9226","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging the efficiency of multi-task robot manipulation via task-evoked planner and reinforcement learning"],"prefix":"10.1109","author":[{"given":"Haofu","family":"Qian","sequence":"first","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Shao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Gu","sequence":"additional","affiliation":[{"name":"Zhejiang Lab,Research Center for Intelligent Robotics,Research Institute of Interdisciplinary Innovation,Hangzhou,China,311100"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University,Hangzhou,China,310030"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"article-title":"A system for general in-hand object re-orientation","volume-title":"Conference on Robot Learning","author":"Chen","key":"ref3"},{"journal-title":"DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation","year":"2022","author":"Qin","key":"ref4"},{"journal-title":"Learning generalizable dexterous manipulation from human grasp affordance","year":"2022","author":"Wu","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160349"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560752"},{"article-title":"Motion planner augmented reinforcement learning for robot manipulation in obstructed environments","volume-title":"Conference on Robot Learning","author":"Yamada","key":"ref10"},{"article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning. PMLR","author":"Sodhani","key":"ref11"},{"journal-title":"Multi-task reinforcement learning with a planning quasi-metric","year":"2020","author":"Micheli","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972794"},{"journal-title":"Soft actor-critic algorithms and applications","year":"2018","author":"Haarnoja","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743795"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160448"},{"key":"ref20","article-title":"Robust reinforcement learning in motion planning","volume":"6","author":"Singh","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561315"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.186"},{"article-title":"Multitask sequence to sequence learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luong","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2598356"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2662006"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"article-title":"Learning an embedding space for transferable robot skills","volume-title":"International Conference on Learning Representations","author":"Hausman","key":"ref30"},{"journal-title":"Multitask reinforcement learning with soft modularization","year":"2020","author":"Yang","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"journal-title":"Policy distillation","year":"2015","author":"Rusu","key":"ref34"},{"key":"ref35","first-page":"4496","article-title":"Dis-tral: Robust multitask reinforcement learning","author":"Teh","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223872"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3071062"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972794"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2022.108098"},{"article-title":"Distilling motion planner augmented policies into visual control policies for robot manipulation","volume-title":"Conference on Robot Learning","author":"Liu","key":"ref40"},{"key":"ref41","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume":"32","author":"Eysenbach","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"Ptr-ppo: Proximal policy optimization with prioritized trajectory replay","year":"2021","author":"Liang","key":"ref42"},{"journal-title":"Multi-task reinforcement learning with a planning quasi-metric","year":"2020","author":"Micheli","key":"ref43"},{"article-title":"Meta-world: A benchmark and evaluation for multitask and meta reinforcement learning","volume-title":"Conference on robot learning","author":"Yu","key":"ref44"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","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\/10611076.pdf?arnumber=10611076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:07:00Z","timestamp":1723349220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611076","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}