{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:05:15Z","timestamp":1764050715587,"version":"3.45.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union through the National Laboratory for Autonomous Systems","award":["RRF-2.3.1-21-2022-00002"],"award-info":[{"award-number":["RRF-2.3.1-21-2022-00002"]}]},{"name":"Ministry of Innovation and Technology of Hungary"},{"DOI":"10.13039\/501100012550","name":"Nemzeti Kutat\u00e1si, Fejleszt\u00e9si \u00e9s Innovaci\u00f3s Alap","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012550","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Culture and Innovation of Hungary from the National Research","award":["KDP-2023","KDP-2021"],"award-info":[{"award-number":["KDP-2023","KDP-2021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tetci.2025.3552696","type":"journal-article","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T20:28:27Z","timestamp":1743625707000},"page":"4026-4036","source":"Crossref","is-referenced-by-count":0,"title":["Learn to Adapt: A Policy for History-Based Online Adaptation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5360-629X","authenticated-orcid":false,"given":"Peter","family":"Farkas","sequence":"first","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"given":"Laszlo","family":"Szoke","sequence":"additional","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6811-2584","authenticated-orcid":false,"given":"Szilard","family":"Aradi","sequence":"additional","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-9672","authenticated-orcid":false,"given":"Tamas","family":"Becsi","sequence":"additional","affiliation":[{"name":"Department of Control for Transportation and Vehicle Systems, Budapest University of Technology and Economics, Budapest, Hungary"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8996652"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1108\/IR-10-2018-0209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01494"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.102"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793742"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560833"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2017.xiii.048"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560837"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref13","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Nagabandi","year":"2018"},{"key":"ref14","first-page":"1319","article-title":"Learning to reinforcement learn","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","author":"Wang","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref17","first-page":"110","article-title":"Multi-agent manipulation via locomotion using hierarchical sim2real","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Nachum","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00166"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3487075.3487177"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9629-x"},{"key":"ref21","article-title":"Understanding domain randomization for sim-to-real transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2022"},{"key":"ref22","article-title":"Environment probing interaction policies","volume-title":"Proc. Int. Conf. Learn. Representations (Poster)","author":"Zhou","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968053"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974685"},{"key":"ref25","article-title":"Reinforcement learning in system identification","volume-title":"Proc. Deep Reinforcement Learn. Workshop NeurIPS","author":"Jose","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.033"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206342"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2294"},{"key":"ref29","first-page":"642","article-title":"Meta reinforcement learning with latent variable Gaussian processes","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","volume":"2","author":"Smundsson","year":"2018"},{"key":"ref30","first-page":"1842","article-title":"Meta-learning with memory-augmented neural networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Santoro","year":"2016"},{"key":"ref31","first-page":"5405","article-title":"Evolved policy gradients","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Houthooft","year":"2018"},{"key":"ref32","article-title":"Improving generalization in meta reinforcement learning using learned objectives","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Kirsch","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20730"},{"key":"ref34","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Lee","year":"2020"},{"key":"ref35","first-page":"9291","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref38","first-page":"3909","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive Q-functions","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Chebotar","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161227"},{"article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","year":"2023","author":"Collaboration","key":"ref40"},{"key":"ref41","first-page":"885","article-title":"RoboNet: Large-scale multi-robot learning","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Dasari","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10121491"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969946"},{"key":"ref45","first-page":"9355","article-title":"Hardware conditioned policies for multi-robot transfer learning","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2018"},{"key":"ref46","first-page":"4455","article-title":"One policy to control them all: Shared modular policies for agent-agnostic control","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Huang","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636628"},{"key":"ref48","first-page":"343","article-title":"Domain separation networks","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Bousmalis","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_10"},{"key":"ref50","article-title":"Know thyself: Transferable visual control policies through robot-awareness","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160761"},{"key":"ref52","first-page":"4467","article-title":"Graph networks as learnable physics engines for inference and control","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Sanchez-Gonzalez","year":"2018"},{"key":"ref53","first-page":"537","article-title":"XIRL: Cross-embodiment inverse reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Zakka","year":"2021"},{"key":"ref54","article-title":"Metamorph: Learning universal controllers with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gupta","year":"2022"},{"article-title":"A generalist dynamics model for control","year":"2023","author":"Schubert","key":"ref55"},{"key":"ref56","article-title":"A generalist agent","volume":"2022","author":"Reed","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref57","first-page":"2257","article-title":"Learning robot manipulation from cross-morphology demonstration","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Salhotra","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref59","first-page":"1893","article-title":"GenLoco: Generalized locomotion controllers for quadrupedal robots","volume-title":"Proc. Conf. Robot Learn.","volume":"205","author":"Feng","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3311\/PPtr.20075"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05982-z"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610485"},{"key":"ref65","first-page":"3100","article-title":"FastRLAP: A system for learning high-speed driving via deep RL and autonomous practicing","volume-title":"Proc. Conf. Robot Learn.","volume":"229","author":"Stachowicz","year":"2023"},{"key":"ref66","article-title":"Demonstrating a walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning","author":"Kostrikov","year":"2023","journal-title":"Robot.: Sci. Syst."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106941"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103421"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.4172\/2168-9695.1000107"},{"year":"2024","key":"ref73","article-title":"Gymnasium documentation - mujoco"},{"year":"2023","key":"ref74","article-title":"Rllib: Industry-grade reinforcement learning  ray 2.9.2"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/11267152\/10947352.pdf?arnumber=10947352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T05:52:20Z","timestamp":1764049940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":74,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2025.3552696","relation":{},"ISSN":["2471-285X"],"issn-type":[{"type":"electronic","value":"2471-285X"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}