{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:25:39Z","timestamp":1740101139560,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956417","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"2430-2436","source":"Crossref","is-referenced-by-count":0,"title":["Data-Efficient Deep Reinforcement Learning with Symmetric Consistency"],"prefix":"10.1109","author":[{"given":"Xianchao","family":"Zhang","sequence":"first","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wentao","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglu","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,School of Software Technology,Dalian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"High-performance neural networks for visual object classification","author":"ciresan","year":"2011","journal-title":"CoRR"},{"key":"ref11","article-title":"Reinforcement learning with augmented data","author":"laskin","year":"2020","journal-title":"Advances in Neural Information Processing Systems 33 Annual Conference on Neural Information Processing Systems 2020 NeurIPS 2020"},{"key":"ref12","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"yarats","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021"},{"key":"ref13","first-page":"5639","article-title":"CURL: contrastive unsupervised representations for reinforcement learning","volume":"119","author":"laskin","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning ICML 2020"},{"key":"ref14","article-title":"Model based reinforcement learning for atari","author":"kaiser","year":"2020","journal-title":"8th International Conference on Learning Representations ICLR 2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proceedings of the 33nd International Conference on Machine Learning ICML 2016"},{"key":"ref17","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"48","author":"wang","year":"2016","journal-title":"Proceedings of the 33nd International Conference on Machine Learning ICML 2016"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref6","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227801"},{"key":"ref2","article-title":"Deepmind control suite","author":"tassa","year":"2018","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref9","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25 26th Annual Conference on Neural Information Processing Systems NeurIPS 2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","first-page":"14322","article-title":"When to use parametric models in reinforcement learning?","author":"van hasselt","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems 2019 NeurIPS 2019"},{"key":"ref21","article-title":"Soft actorcritic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"CoRR"},{"article-title":"Do recent advancements in model-based deep reinforcement learning really improve data efficiency?","year":"2019","author":"kielak","key":"ref24"},{"key":"ref23","article-title":"Data-efficient reinforcement learning with self-predictive representations","author":"schwarzer","year":"2021","journal-title":"9th International Conference on Learning Representations ICLR 2021"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956417.pdf?arnumber=9956417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:07:14Z","timestamp":1671480434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956417","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}