{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:40:32Z","timestamp":1770842432790,"version":"3.50.1"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.K. EPSRC Project Twenty20Insight","award":["EP\/T017627\/1"],"award-info":[{"award-number":["EP\/T017627\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tetci.2021.3082204","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T13:02:51Z","timestamp":1623243771000},"page":"479-488","source":"Crossref","is-referenced-by-count":13,"title":["Reward-Reinforced Generative Adversarial Networks for Multi-Agent Systems"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1894-722X","authenticated-orcid":false,"given":"Changgang","family":"Zheng","sequence":"first","affiliation":[{"name":"Department of Engineering Science, University of Oxford, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-2903","authenticated-orcid":false,"given":"Shufan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computing, Edinburgh Napier University, Edinburgh, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1801-3494","authenticated-orcid":false,"given":"Juan Marcelo","family":"Parra-Ullauri","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, Aston University, Birmingham, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4744-9150","authenticated-orcid":false,"given":"Antonio","family":"Garcia-Dominguez","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, Aston University, Birmingham, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6895-1636","authenticated-orcid":false,"given":"Nelly","family":"Bencomo","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, Aston University, Birmingham, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6036"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2992778"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2926769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref5","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng","year":"2000"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1538788.1538812"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2741505"},{"key":"ref10","first-page":"4565","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2016"},{"key":"ref11","article-title":"Objective-reinforced generative adversarial networks (organ) for sequence generation models","author":"Guimaraes","year":"2017"},{"key":"ref12","volume-title":"Dynamic Programming","author":"Bellman","year":"1957"},{"key":"ref13","article-title":"The numerics of GANs","author":"Mescheder","year":"2017"},{"key":"ref14","article-title":"Towards Principled Methods for Training Generative Adversarial Networks","author":"Arjovsky","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2991774"},{"key":"ref16","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793661"},{"key":"ref21","first-page":"224","article-title":"Generalization and equilibrium in generative adversarial nets (GANs)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5121\/ijwmn.2015.7409"},{"key":"ref23","first-page":"9","article-title":"RSRP and RSRQ measurement in lte","volume":"2","author":"M","year":"2015","journal-title":"Laroccasolutions Technol. Serv."},{"key":"ref24","volume-title":"Estimating Population Density Distribution From Network-Based Mobile Phone Data","author":"Ricciato","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020579"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v6i1.14240"},{"key":"ref27","first-page":"1","article-title":"Conjugate Bayesian analysis of the Gaussian distribution","author":"Murphy","year":"2007"},{"key":"ref28","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"1996"},{"issue":"3-4","key":"ref29","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2018.08.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2869462"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2017.0978"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-55860-335-6.50027-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref37","first-page":"1626","article-title":"Finite-time analysis of distributed td (0) with linear function approximation on multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. PMLR","author":"Doan","year":"2019"},{"key":"ref38","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref39","first-page":"253","article-title":"Context-specific multiagent coordination and planning with factored mdps","volume-title":"Proc. AAAI Conf. Artif. Intell.\/IAAI","author":"Guestrin","year":"2002"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015410"},{"key":"ref41","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref42","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learning. PMLR","author":"Son","year":"2019"},{"key":"ref43","first-page":"3005","article-title":"On the limitations of first-order approximation in gan dynamics","volume-title":"Proc. Int. Conf. Mach. Learn. PMLR","author":"Li","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2019.07.051"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IntelliSys.2017.8324291"},{"key":"ref46","article-title":"The explanation game: Explaining machine learning models with cooperative game theory","author":"Merrick","year":"2019"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/9778849\/09448192.pdf?arnumber=9448192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:00:54Z","timestamp":1705014054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9448192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":46,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2021.3082204","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}