{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:17:54Z","timestamp":1784607474293,"version":"3.55.0"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Italian Ministry for Research in the framework of the 2017 Program for Research Projects of National Interest","award":["2017YKXYXJ"],"award-info":[{"award-number":["2017YKXYXJ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3126658","type":"journal-article","created":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:35:42Z","timestamp":1636410942000},"page":"153171-153187","source":"Crossref","is-referenced-by-count":186,"title":["Crossing the Reality Gap: A Survey on Sim-to-Real Transferability of Robot Controllers in Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3815-6652","authenticated-orcid":false,"given":"Erica","family":"Salvato","sequence":"first","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0867-8388","authenticated-orcid":false,"given":"Gianfranco","family":"Fenu","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5652-2113","authenticated-orcid":false,"given":"Eric","family":"Medvet","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4423-1666","authenticated-orcid":false,"given":"Felice Andrea","family":"Pellegrino","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"CAD2RL: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"arXiv 1611 04201"},{"key":"ref38","first-page":"1","article-title":"A survey on policy search algorithms for learning robot controllers in a handful of trials","volume":"36","author":"chatzilygeroudis","year":"2019","journal-title":"IEEE Trans Robot"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/37.257890","article-title":"Acquiring robot skills via reinforcement learning","volume":"14","author":"gullapalli","year":"1994","journal-title":"IEEE Control Syst"},{"key":"ref32","first-page":"57","author":"durrant-whyte","year":"2012","journal-title":"Learning to control a low-cost manipulator using data-efficient reinforcement learning"},{"key":"ref31","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"ref35","first-page":"1412","article-title":"Learning to walk in 20 minutes","volume":"95585","author":"tedrake","year":"2005","journal-title":"Proc 14th Yale Workshop Adapt Learn Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00043-3"},{"key":"ref28","author":"deisenroth","year":"2013","journal-title":"A Survey on Policy Search for Robotics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1021\/ie900769v"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2012.09.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.38.8.716"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.1999.7099829"},{"key":"ref26","first-page":"1036","article-title":"Reinforcement learning using approximate belief states","author":"rodriguez","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref25","author":"bertsekas","year":"2019","journal-title":"REINFORCEMENT LEARNING AND OPTIMAL CONTROL"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref51","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/s21041067"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref57","article-title":"Solving Rubik’s cube with a robot hand","author":"akkaya","year":"2019","journal-title":"arXiv 1910 07113"},{"key":"ref56","first-page":"6001","article-title":"Sim-to-real transfer learning using robustified controllers in robotic tasks involving complex dynamics","author":"van baar","year":"2019","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"},{"key":"ref55","first-page":"817","article-title":"Sim-to-real transfer with neural-augmented robot simulation","author":"golemo","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref53","first-page":"700","article-title":"Domain randomization for simulation-based policy optimization with transferability assessment","author":"muratore","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref52","first-page":"281","article-title":"Mutual alignment transfer learning","volume":"78","author":"wulfmeier","year":"2017","journal-title":"Proc 1st Annu Conf Robot Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9282951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11552246_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO52101.2021.9596864"},{"key":"ref49","article-title":"Transfer from simulation to real world through learning deep inverse dynamics model","author":"christiano","year":"2016","journal-title":"arXiv 1610 03518"},{"key":"ref7","article-title":"Flexible robotic grasping with sim-to-real transfer based reinforcement learning","author":"breyer","year":"2018","journal-title":"arXiv 1803 04996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59496-5_337"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref45","first-page":"734","article-title":"Sim-to-real reinforcement learning for deformable object manipulation","author":"matas","year":"2018","journal-title":"Proc 2nd Annu Conf Robot Learn (CoRL)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.06.007"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3072675"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3093551"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref43","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Proc 1st Annu Conf Robot Learn (CoRL)"},{"key":"ref73","author":"wymann","year":"2000","journal-title":"TORCS The Open Racing Car Simulator"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref71","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref70","author":"coumans","year":"2016","journal-title":"Bullet Physics SDK"},{"key":"ref76","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"2017","journal-title":"Proc 1st Annu Conf Robot Learn (CoRL)"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref74","article-title":"Progressive neural networks","author":"rusu","year":"2016","journal-title":"arXiv 1606 04671"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778810"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00009"},{"key":"ref60","first-page":"1","article-title":"Grounded action transformation for robot learning in simulation","author":"hanna","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.061"},{"key":"ref63","first-page":"426","article-title":"Deep reinforcement learning: An overview","author":"mousavi","year":"2016","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref65","year":"2020","journal-title":"Blender Open Source 3D Modeling Suit"},{"key":"ref66","year":"2020","journal-title":"Simspark"},{"key":"ref67","year":"2020","journal-title":"Gazebo-robot simulation made easy"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00500"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref69","year":"2001","journal-title":"Vortex Studio Real-time simulation and visualization software for system-level modeling of mechatronics and mechanical equipment"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref109","first-page":"39","article-title":"Humanoid robots learning to walk faster: From the real world to simulation and back","author":"farchy","year":"2013","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1029\/WR025i002p00152"},{"key":"ref107","first-page":"1","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref93","first-page":"1","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc 2nd Int Conf Learn Represent (ICLR)"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32494-1_4"},{"key":"ref92","first-page":"1","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref105","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref104","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/9.29425"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/87.944471"},{"key":"ref111","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2011.5975397"},{"key":"ref110","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref99","article-title":"Adversarial reinforcement learning","author":"uther","year":"1997"},{"key":"ref96","first-page":"945","article-title":"Predictive Q-routing: A memory-based reinforcement learning approach to adaptive traffic control","author":"choi","year":"1996","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1177\/105971239300100403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-46406-9_18"},{"key":"ref12","first-page":"190","author":"nolfi","year":"1994","journal-title":"Artificial Life IV Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012459627968"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2006.340190"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3067695.3082052"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2012.2185849"},{"key":"ref82","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref118","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1910837117"},{"key":"ref81","author":"ackermann","year":"2012","journal-title":"Robust Control The Parameter Space Approach"},{"key":"ref117","article-title":"Improving generalization in meta reinforcement learning using learned objectives","author":"kirsch","year":"2019","journal-title":"arXiv 1910 04098"},{"key":"ref84","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2009.04.007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3182\/20100705-3-BE-2011.00113"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref83","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref114","article-title":"Data-efficient domain randomization with Bayesian optimization","author":"muratore","year":"2020","journal-title":"arXiv 2003 02471"},{"key":"ref113","year":"2020","journal-title":"Poppy Project Open Source Robotics Platform"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2017.05.001"},{"key":"ref116","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"gupta","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00228-9"},{"key":"ref89","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume":"87","author":"kalashnikov","year":"2018","journal-title":"Proc The 2nd Conf Robot Learn"},{"key":"ref120","article-title":"Meta-learning in neural networks: A survey","author":"hospedales","year":"2020","journal-title":"arXiv 2004 05439"},{"key":"ref121","first-page":"5005","article-title":"Least-squares temporal difference learning for the linear quadratic regulator","author":"tu","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref85","article-title":"Memory-based control with recurrent neural networks","author":"heess","year":"2015","journal-title":"arXiv 1512 04455"},{"key":"ref86","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref87","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref88","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecerik","year":"2017","journal-title":"arXiv 1707 08817"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09606868.pdf?arnumber=9606868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:44:43Z","timestamp":1662669883000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9606868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":121,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3126658","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}