{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:30:14Z","timestamp":1770748214259,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3176413","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T19:37:57Z","timestamp":1653075477000},"page":"1-1","source":"Crossref","is-referenced-by-count":40,"title":["Masked Contrastive Representation Learning for Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jinhua","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"}]},{"given":"Yingce","family":"Xia","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, 100080, China"}]},{"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, 100080, China"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Electronic Engineering and Information Science, University of Science and Technology of China, 12652 Hefei, Anhui, China"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, 100080, China"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, 100080, China"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, 230027, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01165"},{"key":"ref7","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref8","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"ref9","article-title":"Suphx: Mastering mahjong with deep reinforcement learning","author":"Li","year":"2020"},{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref11","first-page":"5639","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Laskin"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2899570"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037898"},{"key":"ref14","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016"},{"key":"ref15","first-page":"741","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref17","first-page":"2555","article-title":"Learning latent dynamics for planning from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hafner"},{"key":"ref18","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019"},{"key":"ref19","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019"},{"key":"ref20","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"H\u00e9naff","year":"2019"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref24","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref25","article-title":"Cross-lingual language model pretraining","author":"Lample","year":"2019"},{"key":"ref26","first-page":"14322","article-title":"When to use parametric models in reinforcement learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"van Hasselt"},{"key":"ref27","article-title":"Do recent advancements in model-based deep reinforcement learning really improve data efficiency?","author":"Kielak","year":"2020"},{"key":"ref28","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref29","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2936841"},{"key":"ref33","article-title":"InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"Sun","year":"2019"},{"key":"ref34","article-title":"Contrastive multi-view representation learning on graphs","author":"Hassani","year":"2020"},{"key":"ref35","article-title":"CSTNet: Contrastive speech translation network for self-supervised speech representation learning","author":"Khurana","year":"2020"},{"key":"ref36","article-title":"Loss is its own reward: Self-supervision for reinforcement learning","author":"Shelhamer","year":"2016"},{"key":"ref37","article-title":"Unsupervised control through non-parametric discriminative rewards","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Warde-Farley"},{"key":"ref38","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schwarzer"},{"key":"ref39","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. 34th Conf. Adv. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref40","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats"},{"key":"ref41","article-title":"Achieving human parity on automatic chinese to english news translation","author":"Hassan","year":"2018"},{"key":"ref42","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref43","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref44","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Proc. Adv. Neural Inform. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref48","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3031898"},{"key":"ref50","first-page":"7487","article-title":"Stabilizing transformers for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parisotto"},{"key":"ref51","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref52","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref57","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref58","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fortunato"},{"key":"ref59","first-page":"29304","article-title":"Deep reinforcement learning at the edge of the statistical precipice","author":"Agarwal","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09779589.pdf?arnumber=9779589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:52:16Z","timestamp":1705963936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9779589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3176413","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}