{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:42:20Z","timestamp":1777567340153,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561982","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"45-51","source":"Crossref","is-referenced-by-count":23,"title":["Policy Transfer via Kinematic Domain Randomization and Adaptation"],"prefix":"10.1109","author":[{"given":"Ioannis","family":"Exarchos","sequence":"first","affiliation":[{"name":"Stanford University,Department of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Yu","sequence":"additional","affiliation":[{"name":"Robotics at Google,Mountain View,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Karen Liu","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","volume":"37","author":"mockus","year":"2012","journal-title":"Bayesian Approach to Global Optimization Theory and Applications"},{"key":"ref11","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130833"},{"key":"ref13","first-page":"3834","article-title":"Grounded action transformation for robot learning in simulation","author":"hanna","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.031"},{"key":"ref15","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017"},{"key":"ref16","first-page":"9333","article-title":"Hardware conditioned policies for multi-robot transfer learning","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref18","article-title":"Learning fast adaptation with meta strategy optimization","author":"yu","year":"2019"},{"key":"ref19","article-title":"Learning agile robotic locomotion skills by imitating animals","author":"peng","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","first-page":"1","article-title":"Deepmimic: Example-guided deep reinforcement learning of physics-based character skills","volume":"37","author":"peng","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref5","first-page":"464","article-title":"Why off-the-shelf physics simulators fail in evaluating feedback controller performance-a case study for quadrupedal robots","author":"neunert","year":"2017","journal-title":"Advances in Cooperative Robotics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref7","first-page":"1","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2018","journal-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201397"},{"key":"ref9","article-title":"Policy transfer with strategy optimization","author":"yu","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","article-title":"Solving rubik’s cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/IROS45743.2020.9341571","article-title":"Rapidly adaptable legged robots via evolutionary meta-learning","author":"song","year":"2020"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref24","article-title":"Laikago: Let’s challenge new possibilities","year":"2018"},{"key":"ref23","volume":"2","author":"williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref25","article-title":"Pybullet, a python module for physics simulation in robotics, games and machine learning","author":"coumans","year":"2017"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561982.pdf?arnumber=9561982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:42:35Z","timestamp":1673563355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561982","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}