{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:00:02Z","timestamp":1775066402669,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9196540","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"2725-2731","source":"Crossref","is-referenced-by-count":67,"title":["Meta Reinforcement Learning for Sim-to-real Domain Adaptation"],"prefix":"10.1109","author":[{"given":"Karol","family":"Arndt","sequence":"first","affiliation":[]},{"given":"Murtaza","family":"Hazara","sequence":"additional","affiliation":[]},{"given":"Ali","family":"Ghadirzadeh","sequence":"additional","affiliation":[]},{"given":"Ville","family":"Kyrki","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206046"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2900768"},{"key":"ref11","article-title":"Evolutionary principles in self-referential learning. on learning now to learn: The meta-meta-meta...-hook","author":"schmidhuber","year":"1987","journal-title":"diploma thesis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298591"},{"key":"ref13","first-page":"293","article-title":"Learning to learn","author":"schmidhuber","year":"1998","journal-title":"ch Reinforcement Learning with Self-modifying Policies"},{"key":"ref14","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"2017","journal-title":"ICLRE"},{"key":"ref15","article-title":"Rl2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2017"},{"key":"ref16","first-page":"3556","article-title":"Differentiable plasticity: training plastic neural networks with backpropagation","author":"miconi","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref17","first-page":"5331","article-title":"Efficient offpolicy meta-reinforcement learning via probabilistic context variables","volume":"97","author":"rakelly","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning ICML 2019"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume":"70","author":"finn","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref19","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref28","article-title":"Model-based reinforcement learning via meta-policy optimization","author":"clavera","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref27","first-page":"281","article-title":"Mutual alignment transfer learning","author":"wulfmeier","year":"2017","journal-title":"CoRL 2017-1st Annual Conf Robot Learn"},{"key":"ref3","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":"ref6","article-title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","author":"chebotar","year":"2018"},{"key":"ref29","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref5","article-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"Affordance¨ learning for end-to-end visuomotor robot control","author":"h\u00e4m\u00e4l\u00e4inen","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref9","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","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","author":"levine","year":"2017"},{"key":"ref20","article-title":"How to train your maml","author":"antoniou","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref21","article-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"stadie","year":"2018","journal-title":"CoRR"},{"key":"ref24","article-title":"Sim2real view invariant visual servoing by recurrent control","author":"sadeghi","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"(cad)$ˆ2$rl: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967657"},{"key":"ref25","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09196540.pdf?arnumber=9196540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:16:59Z","timestamp":1656375419000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196540","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}