{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T06:35:44Z","timestamp":1723271744025},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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":["U2013601","62173314","U19B2044","61836011"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tetci.2022.3140380","type":"journal-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:32:23Z","timestamp":1642105943000},"page":"1025-1035","source":"Crossref","is-referenced-by-count":5,"title":["Structural Parameter Space Exploration for Reinforcement Learning via a Matrix Variate Distribution"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-6985-240X","authenticated-orcid":false,"given":"Shaochen","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]},{"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2332-3959","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2069-9544","authenticated-orcid":false,"given":"Zhen","family":"Kan","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref12","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"Comput Res Repository"},{"key":"ref34","first-page":"5574","article-title":"What uncertainties do we need in bayesian deep learning for computer vision","author":"kendall","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 30"},{"key":"ref15","first-page":"3875","article-title":"Self-imitation learning","volume":"80","author":"oh","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","article-title":"Super mario bros for OpenAI gym","author":"kauten","year":"2018","journal-title":"Github"},{"key":"ref30","volume":"3","author":"golub","year":"1996","journal-title":"Matrix Computations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref33","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref10","article-title":"Noisy networks for exploration","author":"fortunato","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref32","first-page":"4148","article-title":"The arcade learning environment: An evaluation platform for general agents (extended abstract)","author":"bellemare","year":"0","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref17","article-title":"UCB and infogain exploration via q-ensembles","author":"chen","year":"2017","journal-title":"Comput Res Repository"},{"key":"ref16","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017","journal-title":"Comput Res Repository"},{"key":"ref19","article-title":"Exploration by random network distillation","author":"burda","year":"2018","journal-title":"Comput Res Repository"},{"key":"ref18","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","author":"houthooft","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 29"},{"key":"ref24","first-page":"1283","article-title":"Learning structured weight uncertainty in bayesian neural networks","volume":"54","author":"sun","year":"0","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref23","first-page":"1613","article-title":"Weight uncertainty in neural networks","volume":"37","author":"blundell","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","first-page":"1137","article-title":"Learning structural weight uncertainty for sequential decision-making","volume":"48","author":"zhang","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref25","first-page":"1708","article-title":"Structured and efficient variational deep learning with matrix gaussian posteriors","volume":"48","author":"louizos","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81283-5_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc 2nd Int Conf Learn Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1201\/9780203749289"},{"key":"ref8","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"0","journal-title":"Proc Adv Neural Inf Process Syst 29"},{"key":"ref7","first-page":"359","article-title":"The KL-UCB algorithm for bounded stochastic bandits and beyond","author":"garivier","year":"0","journal-title":"Proc 24th Annu Conf Learn Theory JMLR Workshop Conf Proc"},{"key":"ref9","article-title":"Parameter space noise for exploration","author":"plappert","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref4","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Comput Res Repository"},{"key":"ref3","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10190085\/09679819.pdf?arnumber=9679819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:31:34Z","timestamp":1691433094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9679819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2022.3140380","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}