{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:33:44Z","timestamp":1777570424475,"version":"3.51.4"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561103","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"13611-13617","source":"Crossref","is-referenced-by-count":81,"title":["Generalization in Reinforcement Learning by Soft Data Augmentation"],"prefix":"10.1109","author":[{"given":"Nicklas","family":"Hansen","sequence":"first","affiliation":[{"name":"University of California,San Diego,CA,USA"}]},{"given":"Xiaolong","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,San Diego,CA,USA"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"kostrikov","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"ref33","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref31","article-title":"Contrastive multiview coding","author":"tian","year":"2019"},{"key":"ref30","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref37","article-title":"Never stop learning: The effectiveness of fine-tuning in robotic reinforcement learning","author":"julian","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197505"},{"key":"ref35","article-title":"Domain adaptation for reinforcement learning on the atari","author":"carr","year":"2019","journal-title":"AAMAS"},{"key":"ref34","article-title":"Data-efficient reinforcement learning with momentum predictive representations","author":"schwarzer","year":"2020"},{"key":"ref10","article-title":"Observational overfitting in reinforcement learning","author":"song","year":"2019"},{"key":"ref40","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"CoRR"},{"key":"ref11","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2019"},{"key":"ref12","article-title":"Asymmetric actor critic for image-based robot learning","author":"pinto","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref15","article-title":"Single episode policy transfer in reinforcement learning","author":"yang","year":"2019"},{"key":"ref16","article-title":"A simple randomization technique for generalization in deep reinforcement learning","author":"lee","year":"2019"},{"key":"ref17","article-title":"Automatic data augmentation for generalization in deep reinforcement learning","author":"raileanu","year":"2020"},{"key":"ref18","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019"},{"key":"ref19","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref4","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref3","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"2019","journal-title":"ICLRE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref8","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2018"},{"key":"ref7","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","author":"gamrian","year":"2019"},{"key":"ref2","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref9","article-title":"Reinforcement learning with augmented data","author":"laskin","year":"2020"},{"key":"ref46","article-title":"What makes for good views for contrastive learning","author":"tian","year":"2020"},{"key":"ref20","article-title":"Decoupling representation learning from reinforcement learning","author":"stooke","year":"0"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref47","article-title":"Places: A 10 million image database for scene recognition","author":"zhou","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref21","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref42","article-title":"Self-supervised policy adaptation during deployment","author":"hansen","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref41","article-title":"Assessing generalization in deep reinforcement learning","author":"packer","year":"2018"},{"key":"ref23","article-title":"DeepMind control suite","author":"tassa","year":"2018"},{"key":"ref44","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref26","first-page":"2536","article-title":"Context encoders: Feature learning by inpainting","author":"pathak","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref43","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561103.pdf?arnumber=9561103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:21:27Z","timestamp":1659482487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561103","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}