{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:54:30Z","timestamp":1730195670922,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T00:00:00Z","timestamp":1620604800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,10]]},"DOI":"10.1109\/aiiot52608.2021.9454208","type":"proceedings-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T20:34:07Z","timestamp":1624307647000},"page":"0275-0281","source":"Crossref","is-referenced-by-count":1,"title":["A Distributed Reinforcement Learning approach for Power Control in Wireless Networks"],"prefix":"10.1109","author":[{"given":"Antonio","family":"Ornatelli","sequence":"first","affiliation":[]},{"given":"Andrea","family":"Tortorelli","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Liberati","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2012.2188912"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2917279"},{"key":"ref33","first-page":"5143","article-title":"Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations","volume":"80","author":"wang","year":"0","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.061"},{"key":"ref31","first-page":"1626","article-title":"Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning","author":"doan","year":"0","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref30","article-title":"Distributed Reinforcement Learning for Cooperative Multi-Robot Object Manipulation","author":"ding","year":"0","journal-title":"Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS)"},{"key":"ref37","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref35","first-page":"921","article-title":"Competing Against Nash Equilibria in Adversarially Changing Zero-Sum Games","author":"cardoso","year":"0","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2679115"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2006.288433"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.01.031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EMNETS.2005.1469097"},{"journal-title":"ETSI Technical Committee Mobile Standards Group (MSG)","year":"2019","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2001.965456"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICUPC.1994.383053"},{"key":"ref15","first-page":"25","article-title":"A power control algorithm for 3G WCDMA system","author":"nuaymi","year":"2002","journal-title":"European Wireless"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA.2011.6137991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/4234.935747"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref28","first-page":"1603","article-title":"Reinforcement learning to play an optimal Nash equilibrium in team Markov games","volume":"15","author":"wang","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2017.2670018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1978.1101791"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7180523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4067\/S0718-18762013000200011"},{"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":"Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2018.08.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/sym12122024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCSS.2011.50"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2018.12.009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s130303473"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2015.06.106"},{"journal-title":"Multi-agent reinforcement learning A selective overview of theories and algorithms","year":"2019","author":"zhang","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(02)00030-X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1515\/9781400835355"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICAT.2009.5348437"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2007.904825"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11424-014-2115-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2004.824698"},{"journal-title":"Wireless Networking","year":"2008","author":"kumar","key":"ref44"},{"key":"ref26","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume":"96","author":"boutilier","year":"1996","journal-title":"TARK"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807213"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00013-4"}],"event":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","start":{"date-parts":[[2021,5,10]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2021,5,13]]}},"container-title":["2021 IEEE World AI IoT Congress (AIIoT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9454163\/9454164\/09454208.pdf?arnumber=9454208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:42:24Z","timestamp":1652197344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9454208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,10]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/aiiot52608.2021.9454208","relation":{},"subject":[],"published":{"date-parts":[[2021,5,10]]}}}