{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:52:18Z","timestamp":1774965138344,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Joint \u00dastav teorie informace a automatizace (UTIA)-Provozn\u011b ekonomick\u00e1 fakulta (PEFT) Laboratory TALISMAN"},{"DOI":"10.13039\/501100000921","name":"European Cooperation in Science and Technology through COST Action","doi-asserted-by":"publisher","award":["CA21169"],"award-info":[{"award-number":["CA21169"]}],"id":[{"id":"10.13039\/501100000921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3497589","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T13:57:40Z","timestamp":1731506260000},"page":"177204-177218","source":"Crossref","is-referenced-by-count":1,"title":["Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9349-377X","authenticated-orcid":false,"given":"Marko","family":"Ruman","sequence":"first","affiliation":[{"name":"Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1017-0727","authenticated-orcid":false,"given":"Tatiana V.","family":"Guy","sequence":"additional","affiliation":[{"name":"Department of Adaptive Systems, Institute of Information Theory and Automation, Czech Academy of Sciences, Prague, Czech Republic"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref2","first-page":"561","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","volume-title":"Proc. Conf. Robot Learn.","author":"Mahmood"},{"key":"ref3","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01130-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref6","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref9","first-page":"1","article-title":"Autonomous cross-domain knowledge transfer in lifelong policy gradient reinforcement learning","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Ammar"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3065710"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01291"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561157"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01117"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3112718"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3249572"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref17","article-title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","author":"Clune","year":"2019","journal-title":"arXiv:1905.10985"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref20","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gamrian"},{"key":"ref21","article-title":"Robust policies via mid-level visual representations: An experimental study in manipulation and navigation","author":"Chen","year":"2020","journal-title":"arXiv:2011.06698"},{"key":"ref22","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"Gupta","year":"2017","journal-title":"arXiv:1703.02949"},{"key":"ref23","first-page":"1","article-title":"Successor features for transfer in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Barreto"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3243631"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref26","first-page":"1","article-title":"Unsupervised image-to-image translation networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref27","article-title":"Learning cross-domain correspondence for control with dynamics cycle-consistency","author":"Zhang","year":"2020","journal-title":"arXiv:2012.09811"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_8"},{"key":"ref29","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in Operations Research and Management Science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"issue":"48","key":"ref31","first-page":"7","article-title":"Approximation with artificial neural networks","volume":"24","author":"Cs\u00e1ji","year":"2001","journal-title":"Fac. Sci., Etvs Lornd Univ., Hung."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref33","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref34","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.31.5.838"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref39","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_35"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref43","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10752398.pdf?arnumber=10752398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T05:10:01Z","timestamp":1752297001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10752398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3497589","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}