{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:19:25Z","timestamp":1756991965516,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812213","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T15:36:40Z","timestamp":1657640200000},"page":"3605-3615","source":"Crossref","is-referenced-by-count":2,"title":["Intrinsically Motivated Self-supervised Learning in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yue","family":"Zhao","sequence":"first","affiliation":[{"name":"Peking University,Haidian, Beijing,China"}]},{"given":"Chenzhuang","family":"Du","sequence":"additional","affiliation":[{"name":"Tsinghua University,Haidian, Beijing,China"}]},{"given":"Hang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Haidian, Beijing,China"}]},{"given":"Tiejun","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,Haidian, Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Exploring simple siamese representation learning","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"shelhamer","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Self-supervised policy adaptation during deployment","author":"hansen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","volume":"34","author":"hansen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref19","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Reinforcement learning with videos: Combining offline observations with interaction","author":"schmeckpeper","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref5","article-title":"Improving sample efficiency in model-free reinforcement learning from images","author":"yarats","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref8","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"srinivas","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref1","article-title":"Generalization in reinforcement learning by soft data augmentation","author":"hansen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Ex2: Exploration with exemplar models for deep reinforcement learning","author":"fu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"222","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"0","journal-title":"Proc of the International Conference on Simulation of Adaptive Behavior From Animals to Animats"},{"journal-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","year":"2021","author":"hansen","key":"ref24"},{"key":"ref23","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref25","article-title":"The distracting control suite-a challenging benchmark for reinforcement learning from pixels","author":"stone","year":"2021","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2022,5,23]]},"location":"Philadelphia, PA, USA","end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812213.pdf?arnumber=9812213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T19:09:06Z","timestamp":1667502546000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812213\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812213","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}