{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T05:36:59Z","timestamp":1737005819926,"version":"3.33.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute for Information and Communications Technology Promotion (IITP) Grant funded by the Korea Government [Ministry of Science and ICT (MSIT)]"},{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology (KIAT) Grant funded by the Korea Government [Ministry of Trade, Industry and Energy (MOTIE)]","doi-asserted-by":"publisher","award":["P0017033"],"award-info":[{"award-number":["P0017033"]}],"id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IITP Grant funded by the Korean Government (MSIT), Artificial Intelligence Convergence Innovation Human Resources Development","award":["RS-2022-00155911"],"award-info":[{"award-number":["RS-2022-00155911"]}]},{"name":"Convergence Security Core Talent Training Business Support Program","award":["IITP-2023-RS-2023-00266615"],"award-info":[{"award-number":["IITP-2023-RS-2023-00266615"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3526959","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:25:08Z","timestamp":1736367908000},"page":"7939-7950","source":"Crossref","is-referenced-by-count":0,"title":["Mix-Spectrum for Generalization in Visual Reinforcement Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5862-0124","authenticated-orcid":false,"given":"Jeong Woon","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Software Convergence, Kyung Hee University, Yongin, Gyeonggi, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3241-8455","authenticated-orcid":false,"given":"Hyoseok","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Software Convergence, Kyung Hee University, Yongin, Gyeonggi, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A comprehensive survey of data augmentation in visual reinforcement learning","author":"Ma","year":"2022","journal-title":"arXiv:2210.04561"},{"key":"ref2","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref3","first-page":"1","article-title":"Observational overfitting in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"},{"key":"ref5","first-page":"20393","article-title":"Spectrum random masking for generalization in image-based reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang"},{"key":"ref6","first-page":"1","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yarats"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01133"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109474"},{"key":"ref9","first-page":"1","article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref10","first-page":"1","article-title":"Robust and generalizable visual representation learning via random convolutions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00994"},{"key":"ref12","first-page":"3680","article-title":"Stabilizing deep Q-learning with ConvNets and vision transformers under data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hansen"},{"key":"ref13","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"issue":"1","key":"ref15","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":"ref16","first-page":"1","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Nair"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560925"},{"key":"ref19","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref20","first-page":"25476","article-title":"Mastering Atari games with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ye"},{"key":"ref21","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref22","first-page":"5276","article-title":"PlayVirtual: Augmenting cycle-consistent virtual trajectories for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561103"},{"key":"ref29","first-page":"66","article-title":"Learning by cheating","volume-title":"Proc. Conf. Robot Learn.","author":"Chen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref31","first-page":"3088","article-title":"SECANT: Self-expert cloning for zero-shot generalization of visual policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fan"},{"key":"ref32","first-page":"1","article-title":"Domain generalization with mixstyle","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_35"},{"key":"ref34","first-page":"1137","article-title":"Normalization enhances generalization in visual reinforcement learning","volume-title":"Proc. 23rd Int. Conf. Auto. Agents Multiagent Syst.","author":"Li"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81897-4_4"},{"key":"ref36","first-page":"1","article-title":"Mixup: Beyond empirical risk management","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref37","article-title":"k-mixup regularization for deep learning via optimal transport","volume":"2023","author":"Greenewald","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref38","article-title":"DeepMind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","first-page":"5402","article-title":"Automatic data augmentation for generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raileanu"},{"key":"ref41","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref42","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gidaris"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548267"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2012.03.039"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01628"},{"issue":"11","key":"ref46","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10833629.pdf?arnumber=10833629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:14:36Z","timestamp":1736972076000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10833629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3526959","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}