{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:05:24Z","timestamp":1740099924480,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341124","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"4403-4410","source":"Crossref","is-referenced-by-count":2,"title":["Adaptability Preserving Domain Decomposition for Stabilizing Sim2Real Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Haichuan","family":"Gao","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhile","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Su","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Tan","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00493"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref13","article-title":"Active domain randomization","author":"mehta","year":"2019","journal-title":"Conference on Robot Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref15"},{"key":"ref16","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968596"},{"key":"ref18","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593933"},{"article-title":"Subjectivity learning theory towards artificial general intelligence","year":"2019","author":"su","key":"ref28"},{"article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","year":"2016","author":"christiano","key":"ref4"},{"article-title":"Memory-based control with recurrent neural networks","year":"2015","author":"heess","key":"ref27"},{"key":"ref3","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Conference on Robot Learning"},{"article-title":"Modular deep q networks for sim-to-real transfer of visuo-motor policies","year":"2017","author":"zhang","key":"ref6"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref29"},{"article-title":"3D simulation for robot arm control with deep q-learning","year":"2016","author":"james","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919870227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2894216"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794126"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"article-title":"Data-efficient learning for sim-to-real robotic grasping using deep point cloud prediction networks","year":"2019","author":"yan","key":"ref21"},{"key":"ref24","article-title":"Universal value function approximators","author":"schaul","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"article-title":"Robust domain randomization for reinforcement learning","year":"2019","author":"slaoui","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341124.pdf?arnumber=9341124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:22Z","timestamp":1656453442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341124","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}