{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T22:18:29Z","timestamp":1771539509459,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icra48506.2021.9561731","type":"proceedings-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T20:28:35Z","timestamp":1634675315000},"page":"2884-2890","source":"Crossref","is-referenced-by-count":37,"title":["SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yifeng","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Tingnan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Ho","sequence":"additional","affiliation":[]},{"given":"Yunfei","family":"Bai","sequence":"additional","affiliation":[]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Tan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Discriminator-actor-critic: Addressing sample inefficiency and reward bias in adversarial imitation learning","author":"kostrikov","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref38","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Learning to simulate","author":"ruiz","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref31","article-title":"Cad2rl: Real single-image flight without a single real image","author":"sadeghi","year":"2016"},{"key":"ref30","article-title":"Modelling generalized forces with reinforcement learning for sim-to-real transfer","author":"jeong","year":"2019"},{"key":"ref37","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"fu","year":"2017"},{"key":"ref36","article-title":"Rlcyclegan: Reinforcement learning aware simulation-to-real","author":"rao","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref34","article-title":"Using simulation and domain adaptation to improve efficiency of deep robotic grasping","author":"bousmalis","year":"2017"},{"key":"ref10","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume":"78","author":"rusu","year":"0"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref11","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","author":"yang","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref12","article-title":"Stochastic grounded action transformation for robot learning in simulation","author":"desai","year":"2020","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems(IROS 2020)"},{"key":"ref13","article-title":"Provably efficient model-based policy adaptation","author":"song","year":"2020"},{"key":"ref14","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":"ref15","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974685"},{"key":"ref18","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"eysenbach","year":"2020"},{"key":"ref19","article-title":"Humanoid robots learning to walk faster: From the real world to simulation and back","author":"farchy","year":"0"},{"key":"ref28","article-title":"An imitation from observation approach to transfer learning with dynamics mismatch","author":"desai","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"zhu","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/451"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341701"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.064","article-title":"Learning agile robotic locomotion skills by imitating animals","author":"peng","year":"2020","journal-title":"Robotics Science and Systems"},{"key":"ref9","article-title":"Active domain randomization","author":"mehta","year":"2019"},{"key":"ref1","article-title":"Solving rubik’s cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref46","article-title":"CMA-ES\/pycma on Github","author":"hansen","year":"2019","journal-title":"Zenodo"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759424"},{"key":"ref45","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/027836499201100408"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495932"},{"key":"ref42","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref24","article-title":"Epopt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/IROS45743.2020.9340801","article-title":"Adversarial generation of informative trajectories for dynamics system identification","author":"jegorova","year":"2020"},{"key":"ref44","article-title":"Pybullet, a python module for physics simulation in robotics, games and machine learning","author":"coumans","year":"2017"},{"key":"ref26","article-title":"Bayesian domain randomization for sim-to-real transfer","author":"muratore","year":"2020"},{"key":"ref43","article-title":"Laikago: Let’s challenge new possibilities","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"}],"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\/09561731.pdf?arnumber=9561731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T17:51:03Z","timestamp":1673545863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561731","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}