{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:18:09Z","timestamp":1771658289460,"version":"3.50.1"},"reference-count":51,"publisher":"Zhejiang University Press","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1631\/fitee.2400406","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T04:14:11Z","timestamp":1741234451000},"page":"385-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Significance extraction based on data augmentation for reinforcement learning","\u57fa\u4e8e\u6570\u636e\u589e\u5f3a\u7684\u663e\u8457\u6027\u63d0\u53d6\u5f3a\u5316\u5b66\u4e60"],"prefix":"10.1631","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5319-006X","authenticated-orcid":false,"given":"Yuxi","family":"Han","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4329-864X","authenticated-orcid":false,"given":"Dequan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[]}],"member":"635","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"ref1","author":"Almuzairee","year":"2024","journal-title":"A recipe for unbounded data augmentation in visual reinforcement learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561915"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2743240"},{"key":"ref4","article-title":"Look where you look! Saliency-guided Q-networks for generalization in visual reinforcement learning","volume-title":"Proc 36th Int Conf on Neural Information Processing Systems","author":"Bertoin","year":"2022"},{"key":"ref5","first-page":"1597","article-title":"A simple frame-work for contrastive learning of visual representations","volume-title":"Proc 37th Int Conf on Machine Learning","author":"Chen","year":"2020"},{"key":"ref6","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc 36th Int Conf on Machine Learning","author":"Cobbe","year":"2019"},{"key":"ref7","author":"Farebrother","year":"2018","journal-title":"Generalization and regularization in DQN"},{"key":"ref8","first-page":"3480","article-title":"Learning task in-formed abstractions","volume-title":"Proc 38th Int Conf on Machine Learning","author":"Fu","year":"2021"},{"key":"ref9","first-page":"2063","article-title":"Transfer learning for re-lated reinforcement learning tasks via image- to- image translation","volume-title":"Proc 36th Int Conf on Machine Learning","author":"Gamrian","year":"2019"},{"key":"ref10","first-page":"2170","article-title":"DeepMDP: learning continuous latent space models for representation learning","volume-title":"Proc 36th Int Conf on Machine Learning","author":"Gelada","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.65109\/YPTR7088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561103"},{"key":"ref13","article-title":"Self-supervised policy adaptation during deployment","volume-title":"Proc 9th Int Conf on Learning Representations","author":"Hansen","year":"2021a"},{"key":"ref14","article-title":"Stabilizing deep Q-learning with Conv Nets and vision Transformers under data augmentation","volume-title":"Proc 35th Int Conf on Neural In-formation Processing Systems","author":"Hansen","year":"2021b"},{"key":"ref15","article-title":"On pre-training for visuo-motor control: revisiting a learning-from-scratch baseline","volume-title":"Proc 40th Int Conf on Machine Learning","author":"Hansen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/s0004-3702(98)00023-x"},{"key":"ref18","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manip-ulation","volume-title":"Proc 2nd Conf on Robot Learning","author":"Kalashnikov","year":"2018"},{"key":"ref19","author":"Khraishi","year":"2023","journal-title":"Simple noisy environment augmentation for reinforcement learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-092451"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"key":"ref23","article-title":"Reinforcement learning with augmented data","volume-title":"Proc 34th Int Conf on Neural Information Processing Systems","author":"Laskin","year":"2020b"},{"key":"ref24","article-title":"Network randomization: a simple technique for generalization in deep re-inforcement learning","volume-title":"Proc 8th Int Conf on Learning Representations","author":"Lee","year":"2020"},{"issue":"1","key":"ref25","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":"ref26","first-page":"4772","article-title":"Adaptive aux-iliary task weighting for reinforcement learning","volume-title":"Proc 33rd Conf on Neural Information Processing Systems","author":"Lin","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/880"},{"key":"ref28","author":"Mnih","year":"2013","journal-title":"Playing Atari with deep reinforcement learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref30","first-page":"9209","article-title":"Visual reinforcement learning with imagined goals","volume-title":"Proc 32nd Int Conf on Neural Information Processing Systems","author":"Nair","year":"2018"},{"key":"ref31","author":"Akkaya","year":"2019","journal-title":"Solving Rubik\u2019s cube with a robot hand"},{"key":"ref32","author":"Pinto","year":"2018","journal-title":"Asym-metric actor critic for image-based robot learning"},{"key":"ref33","first-page":"907","article-title":"S4RL: surprisingly simple self-supervision for offline reinforcement learning in robotics","volume-title":"Proc 5th Conf on Robot Learning","author":"Sinha","year":"2022"},{"key":"ref34","article-title":"Observational over-fitting in reinforcement learning","volume-title":"Proc 8th Int Conf on Learning Representations","author":"Song","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref36","author":"Tassa","year":"2018","journal-title":"DeepMind Control Suite"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2017.8202133"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00661"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17251"},{"key":"ref40","article-title":"MoVie: visual model-based policy adaptation for view generalization","volume-title":"Proc 37th Int Conf on Neural Information Processing Systems","author":"Yang","year":"2023"},{"key":"ref41","article-title":"Visual semantic navigation using scene priors","volume-title":"Proc 7th Int Conf on Learning Representations","author":"Yang","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref43","article-title":"Image augmentation is all you need: regularizing deep reinforcement learning from pixels","volume-title":"Proc 9th Int Conf on Learning Representations","author":"Yarats","year":"2021"},{"key":"ref44","first-page":"25117","article-title":"Mask-based la-tent reconstruction for reinforcement learning","volume-title":"Proc 36th Conf on Neural Information Processing Systems","author":"Yu","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3259681"},{"key":"ref46","author":"Zhang","year":"2018","journal-title":"A dissection of overfitting and generalization in continuous reinforcement learning"},{"key":"ref47","article-title":"Learning invariant representations for reinforcement learning without reconstruction","volume-title":"Proc 9th Int Conf on Learning Representations","author":"Zhang","year":"2021"},{"key":"ref48","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume-title":"Proc 34th Int Conf on Neural Information Processing Systems","author":"Zhang","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100594"},{"key":"ref50","author":"Zhou","year":"2024","journal-title":"Continuous control reinforcement learning: distributed distributional DrQ algorithms"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/icra.2017.7989381"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2400406.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2400406\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2400406.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:59:01Z","timestamp":1771657141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2400406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["406"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2400406","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"17 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All the authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}