{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:56:51Z","timestamp":1773928611624,"version":"3.50.1"},"reference-count":23,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341019","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"6112-6117","source":"Crossref","is-referenced-by-count":8,"title":["Learning Domain Randomization Distributions for Training Robust Locomotion Policies"],"prefix":"10.1109","author":[{"given":"Melissa","family":"Mozian","sequence":"first","affiliation":[]},{"given":"Juan","family":"Camilo Gamboa Higuera","sequence":"additional","affiliation":[]},{"given":"David","family":"Meger","sequence":"additional","affiliation":[]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102603"},{"key":"ref11","volume":"104","author":"zhou","year":"1998","journal-title":"Essentials of Robust Control"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007327622663"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9561","article-title":"Optimizing the cvar via sampling","author":"tamar","year":"2015","journal-title":"Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref15","article-title":"Contextual policy optimisation","volume":"abs 1805 10662","author":"paul","year":"2018","journal-title":"CoRR"},{"key":"ref16","article-title":"Active domain randomization","volume":"abs 1904 4762","author":"mehta","year":"2019","journal-title":"CoRR"},{"key":"ref17","article-title":"Solving rubik’s cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref18","article-title":"Policy transfer with strategy optimization","volume":"abs 1810 5751","author":"yu","year":"2018","journal-title":"CoRR"},{"key":"ref19","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019"},{"key":"ref4","first-page":"9355","article-title":"Hardware conditioned policies for multi-robot transfer learning","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018"},{"key":"ref6","article-title":"Assessing generalization in deep reinforcement learning","author":"packer","year":"2018"},{"key":"ref5","article-title":"EPOpt: Learning robust neural network policies using model ensembles","volume":"abs 1610 1283","author":"rajeswaran","year":"2016","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"ref7","article-title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","author":"chebotar","year":"2018"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref9","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref21","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1016\/S0927-0507(06)13019-4","article-title":"Gradient estimation","volume":"13","author":"fu","year":"2006","journal-title":"Handbooks in Operations Research and Management Science"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"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\/09341019.pdf?arnumber=9341019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T14:52:28Z","timestamp":1671634348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341019","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}