{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T22:14:35Z","timestamp":1793484875390,"version":"4.5.0"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8460528","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:28:03Z","timestamp":1537554483000},"page":"3803-3810","source":"Crossref","is-referenced-by-count":912,"title":["Sim-to-Real Transfer of Robotic Control with Dynamics Randomization"],"prefix":"10.1109","author":[{"given":"Xue Bin","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcin","family":"Andrychowicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wojciech","family":"Zaremba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"abs 1706 2275","author":"lowe","year":"2017","journal-title":"CoRR"},{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"In Advances in Neural Information Processing Systems 12"},{"key":"ref32","article-title":"Policy transfer via modularity","author":"ignasi clavera","year":"2017","journal-title":"IROS IEEE"},{"key":"ref31","article-title":"Unsupervised learning for physical interaction through video prediction","volume":"abs 1605 7157","author":"finn","year":"2016","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/027836499801700107"},{"key":"ref37","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"abs 1605 6676","author":"foerster","year":"2016","journal-title":"CoRR"},{"key":"ref36","article-title":"Memory-based control with recurrent neural networks","volume":"abs 1512 4455","author":"heess","year":"2015","journal-title":"CoRR"},{"key":"ref35","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"1312","article-title":"Universal value function approximators","volume":"37","author":"schaul","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref10","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"abs 1603 2199","author":"levine","year":"2016","journal-title":"CoRR"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref11","article-title":"Adapting deep visuomotor representations with weak pairwise constraints","volume":"abs 1511 7111","author":"tzeng","year":"2015","journal-title":"CoRR"},{"key":"ref12","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref13","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume":"abs 1703 2949","author":"gupta","year":"2017","journal-title":"CoRR"},{"key":"ref14","article-title":"Learning transferable policies for monocular reactive MAV control","volume":"abs 1608 627","author":"daftry","year":"2016","journal-title":"CoRR"},{"key":"ref15","article-title":"Mutual alignment transfer learning","volume":"abs 1707 7907","author":"wulfmeier","year":"2017","journal-title":"CoRR"},{"key":"ref16","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume":"abs 1610 4286","author":"rusu","year":"2016","journal-title":"CoRR"},{"key":"ref17","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","volume":"abs 1610 3518","author":"christiano","year":"2016","journal-title":"CoRR"},{"key":"ref18","article-title":"Cad2rl: Real single-image flight without a single real image","volume":"abs 1611 4201","author":"sadeghi","year":"2016","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.009"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/2897824.2925881","article-title":"Terrain-adaptive locomotion skills using deep reinforcement learning","volume":"35","author":"peng","year":"2016","journal-title":"ACM Trans on Graphics (Proc of SIGGRAPH)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/027836499601500602"},{"key":"ref3","article-title":"Benchmarking deep reinforcement learning for continuous control","volume":"abs 1604 6778","author":"duan","year":"2016","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"29:1","DOI":"10.1145\/3083723","article-title":"Learning to schedule control fragments for physics-based characters using deep q-learning","volume":"36","author":"liu","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref29","first-page":"278364917698749","article-title":"Parameter and contact force estimation of planar rigid-bodies undergoing frictional contact","volume":"0","author":"fazeli","year":"2016","journal-title":"The International Journal of Robotics Research"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1145\/3072959.3073602","article-title":"Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning","volume":"36","author":"peng","year":"2017","journal-title":"ACM Trans on Graphics (Proc of SIGGRAPH)"},{"key":"ref8","article-title":"Learning contact-rich manipulation skills with guided policy search","volume":"abs 1501 5611","author":"levine","year":"2015","journal-title":"CoRR"},{"key":"ref7","article-title":"Emergence of locomotion behaviours in rich environments","volume":"abs 1707 2286","author":"heess","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref9","article-title":"End-to-end training of deep visuomotor policies","volume":"abs 1504 702","author":"levine","year":"2015","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"3d simulation for robot arm control with deep q-learning","volume":"abs 1609 3759","author":"james","year":"2016","journal-title":"CoRR"},{"key":"ref22","article-title":"Epopt: Learning robust neural network policies using model ensembles","volume":"abs 1610 1283","author":"rajeswaran","year":"2016","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref24","article-title":"Preparing for the unknown: Learning a universal policy with online system identification","volume":"abs 1702 2453","author":"yu","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"Robust adversarial reinforcement learning","volume":"abs 1703 2702","author":"pinto","year":"2017","journal-title":"CoRR"},{"key":"ref26","article-title":"More than a million ways to be pushed: A high-fidelity experimental data set of planar pushing","volume":"abs 1604 4038","author":"yu","year":"2016","journal-title":"CoRR"},{"key":"ref25","article-title":"Reinforcement learning for pivoting task","volume":"abs 1703 472","author":"antonova","year":"2017","journal-title":"CoRR"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08460528.pdf?arnumber=8460528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:40:42Z","timestamp":1598211642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8460528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8460528","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}