{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:30:08Z","timestamp":1781368208157,"version":"3.54.1"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,1]]},"DOI":"10.1109\/ssci47803.2020.9308468","type":"proceedings-article","created":{"date-parts":[[2021,1,5]],"date-time":"2021-01-05T23:12:38Z","timestamp":1609888358000},"page":"737-744","source":"Crossref","is-referenced-by-count":672,"title":["Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey"],"prefix":"10.1109","author":[{"given":"Wenshuai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge Pena","family":"Queralta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomi","family":"Westerlund","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.10.043"},{"key":"ref72","article-title":"Reinforcement learning with perturbed rewards","author":"wang yang liu","year":"2020","journal-title":"AAAI"},{"key":"ref71","article-title":"Domain separation networks","author":"bousmalis","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref77","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref75","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LARS-SBR-WRE48964.2019.00060"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref33","author":"jeong","year":"2019","journal-title":"Modelling generalized forces with reinforcement learning for simto- real transfer"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/ab3c15"},{"key":"ref31","author":"kaspar","year":"2020","journal-title":"Sim2real transfer for reinforcement learning without dynamics randomization"},{"key":"ref30","author":"balaji","year":"2019","journal-title":"DeepRacer Educational Autonomous Racing Platform for Experimentation with Sim2Real Reinforcement Learning"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE48301.2019.9043822"},{"key":"ref36","author":"bassani","year":"2020","journal-title":"Learning to play soccer by reinforcement and applying sim-to-real to compete in the real world"},{"key":"ref35","author":"van baar","year":"2018","journal-title":"Simulation to real transfer learning with robustified policies for robot tasks"},{"key":"ref34","article-title":"Flexible robotic grasping with sim-to-real transfer based reinforcement learning","author":"breyer","year":"2018","journal-title":"ArXiv e-prints"},{"key":"ref60","article-title":"Cycada: Cycle-consistent adversarial domain adaptation","author":"hoffman","year":"2018","journal-title":"ICML"},{"key":"ref62","author":"gupta","year":"2017","journal-title":"Learning invariant feature spaces to transfer skills with reinforcement learning"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref63","author":"higgins","year":"2017","journal-title":"Darla Improving zero-shot transfer in reinforcement learning"},{"key":"ref28","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref64","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref27","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref65","author":"tzeng","year":"2014","journal-title":"Deep domain confusion Maximizing for domain invariance"},{"key":"ref66","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"ICML"},{"key":"ref29","author":"yan","year":"2017","journal-title":"Sim-toreal transfer of accurate grasping with eye-in-hand observations and continuous control"},{"key":"ref67","author":"sun","year":"2015","journal-title":"Return of frustratingly easy domain adaptation"},{"key":"ref68","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","author":"berner","year":"2019","journal-title":"Dota 2 with large scale deep reinforcement learning"},{"key":"ref22","author":"wang","year":"2016","journal-title":"Learning to reinforcement learn"},{"key":"ref21","author":"rusu","year":"2015","journal-title":"Policy distillation"},{"key":"ref24","author":"tessler","year":"2019","journal-title":"Action robust reinforcement learning and applications in continuous control"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053011528"},{"key":"ref26","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref25","author":"mankowitz","year":"2019","journal-title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification"},{"key":"ref50","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/21.179842"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_43"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref52","author":"tobin","year":"2019","journal-title":"Real-World Robotic Perception and Control Using Synthetic Data"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11436"},{"key":"ref11","author":"arndt","year":"2019","journal-title":"Meta reinforcement learning for sim-to-real domain adaptation"},{"key":"ref40","author":"kaspar","year":"0","journal-title":"Reinforcement learning with cartesian commands and sim to real transfer for peg in hole tasks"},{"key":"ref12","author":"traor\u00e9","year":"2019","journal-title":"Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref14","author":"dosovitskiy","year":"2017","journal-title":"CARLA An Open Urban Driving Simulator"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ECMR.2019.8870934"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref19","article-title":"Collaborative multi-robot systems for search and rescue: Coordination and perception","author":"pe\u00f1na queralta","year":"2020","journal-title":"arXiv preprint arXiv 2008 12610"},{"key":"ref80","article-title":"A survey on visual navigation for artificial agents with deep reinforcement learning","author":"zeng","year":"2020","journal-title":"IEEE Access"},{"key":"ref4","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"gar?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"ref6","author":"matas","year":"2018","journal-title":"Sim-to-real reinforcement learning for deformable object manipulation"},{"key":"ref5","author":"rajeswaran","year":"2017","journal-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations"},{"key":"ref8","article-title":"Towards closing the sim-to-real gap in collaborative multi-robot deep reinforcement learning","author":"zhao","year":"2020","journal-title":"5th ICRAE"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref49","author":"haarnoja","year":"2018","journal-title":"Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor"},{"key":"ref9","author":"muratore","year":"2020","journal-title":"Bayesian domain randomization for sim-to-real transfer"},{"key":"ref46","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref45","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref48","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref47","author":"abdolmaleki","year":"2018","journal-title":"Max-imum a posteriori policy optimisation"},{"key":"ref42","author":"pedersen","year":"2019","journal-title":"Sim-to-real transfer of robotic gripper pose estimation-using deep reinforcement learning generative adversarial networks and visual servoing"},{"key":"ref41","author":"hundt","year":"2019","journal-title":"“good robot!” Efficient reinforcement learning for multi-step visual tasks via reward shaping"},{"key":"ref44","author":"nachum","year":"2019","journal-title":"Multi-agent manipulation via locomotion using hierarchical sim2real"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197512"}],"event":{"name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Canberra, ACT, Australia","start":{"date-parts":[[2020,12,1]]},"end":{"date-parts":[[2020,12,4]]}},"container-title":["2020 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9308061\/9308107\/09308468.pdf?arnumber=9308468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T15:18:14Z","timestamp":1656602294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9308468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/ssci47803.2020.9308468","relation":{},"subject":[],"published":{"date-parts":[[2020,12,1]]}}}