{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T11:41:00Z","timestamp":1696333260685},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836011"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2018497"],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MCC Lab of Information Science and Technology Institution"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tg.2022.3164470","type":"journal-article","created":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T20:49:42Z","timestamp":1649105382000},"page":"337-347","source":"Crossref","is-referenced-by-count":0,"title":["Improving Deep Reinforcement Learning With Mirror Loss"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7984-7823","authenticated-orcid":false,"given":"Weide","family":"Shu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-4610-3545","authenticated-orcid":false,"given":"Youpeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering, and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering, and Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3360","article-title":"EMI: Exploration with mutual information","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref12","first-page":"3928","article-title":"Stable reinforcement learning with autoencoders for tactile and visual data","author":"hoof","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref15","article-title":"OpenAI gym","author":"brockman","year":"2016"},{"key":"ref37","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"8769","article-title":"Unsupervised state representation learning in Atari","author":"anand","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","article-title":"Symmetry learning for function approximation in reinforcement learning","author":"mahajan","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2651887"},{"key":"ref11","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref10","article-title":"Towards a definition of disentangled representations","author":"higgins","year":"2018"},{"key":"ref32","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref1","article-title":"Dota 2 with large scale deep reinforcement learning","author":"openai","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00505"},{"key":"ref16","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref38","article-title":"OpenAI baselines","author":"dhariwal","year":"2017"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref18","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2848913"},{"key":"ref23","first-page":"998","article-title":"Playing Atari with six neurons","author":"giuseppe","year":"0","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-85148-3_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: A review and new perspectives","volume":"35","author":"yoshua","year":"2013","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref42","first-page":"5694","article-title":"Imagination-augmented agents for deep reinforcement learning","volume":"30","author":"racani\u00e8re","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2866036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.057"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2899159"},{"key":"ref28","first-page":"2537","article-title":"Deep symmetry networks","volume":"27","author":"gens","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2009.41"},{"key":"ref29","first-page":"1","article-title":"Learning to play Othello with N-tuple systems","volume":"4","author":"lucas","year":"2008","journal-title":"Austral J Intell Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","article-title":"Auto-encoding variational bayes","author":"diederik","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2835764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.110"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref40","article-title":"Suphx: Mastering Mahjong with deep reinforcement learning","author":"li","year":"2020"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10251473\/09748993.pdf?arnumber=9748993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:13:18Z","timestamp":1696270398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9748993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3164470","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}