{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T12:07:19Z","timestamp":1785758839140,"version":"3.56.0"},"reference-count":23,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["2021R1A4A1030075"],"award-info":[{"award-number":["2021R1A4A1030075"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3178194","type":"journal-article","created":{"date-parts":[[2022,5,26]],"date-time":"2022-05-26T19:35:42Z","timestamp":1653593742000},"page":"57369-57382","source":"Crossref","is-referenced-by-count":5,"title":["A Swapping Target Q-Value Technique for Data Augmentation in Offline Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2286-3216","authenticated-orcid":false,"given":"Ho-Taek","family":"Joo","sequence":"first","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9409-9253","authenticated-orcid":false,"given":"In-Chang","family":"Baek","sequence":"additional","affiliation":[{"name":"AI Graduate School, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7732-0817","authenticated-orcid":false,"given":"Kyung-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794126"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref6","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref7","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref8","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref9","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref10","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Wang","year":"2020"},{"key":"ref11","volume-title":"AWAC: Accelerating Online Reinforcement Learning With Offline Datasets","author":"Nair","year":"2021"},{"key":"ref12","article-title":"Reinforcement learning with augmented data","author":"Laskin","year":"2020","journal-title":"arXiv:2004.14990"},{"key":"ref13","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"Srinivas","year":"2020","journal-title":"arXiv:2004.04136"},{"key":"ref14","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020","journal-title":"arXiv:2004.13649"},{"key":"ref15","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref16","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja"},{"key":"ref17","article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","author":"Lee","year":"2019","journal-title":"arXiv:1910.05396"},{"key":"ref18","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref19","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref21","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref23","article-title":"DeepMind control suite","author":"Tassa","year":"2018","journal-title":"arXiv:1801.00690"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09782432.pdf?arnumber=9782432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T01:50:33Z","timestamp":1706752233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9782432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3178194","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}