{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:10:50Z","timestamp":1780510250818,"version":"3.54.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-16-1-2710 P00002"],"award-info":[{"award-number":["N00014-16-1-2710 P00002"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8650-15-C-7556"],"award-info":[{"award-number":["FA8650-15-C-7556"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF","award":["2229876"],"award-info":[{"award-number":["2229876"]}]},{"name":"DHS"},{"name":"IBM"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tac.2024.3403693","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T17:31:56Z","timestamp":1716312716000},"page":"7824-7831","source":"Crossref","is-referenced-by-count":4,"title":["RL-ARNE: A Reinforcement Learning Algorithm for Computing Average Reward Nash Equilibrium of Nonzero-Sum Stochastic Games"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7776-7865","authenticated-orcid":false,"given":"Dinuka","family":"Sahabandu","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6091-2384","authenticated-orcid":false,"given":"Shana","family":"Moothedath","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5503-4123","authenticated-orcid":false,"given":"Joey","family":"Allen","sequence":"additional","affiliation":[{"name":"Palo Alto Networks, 3000 Tannery Way, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8751-2409","authenticated-orcid":false,"given":"Linda","family":"Bushnell","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2761-1277","authenticated-orcid":false,"given":"Wenke","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0269-8097","authenticated-orcid":false,"given":"Radha","family":"Poovendran","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0040-5809(90)90011-J"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161031"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10207-004-0060-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.36.1.48"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177693059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2_10"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/bf01415989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref12","article-title":"Learning average reward irreducible stochastic games: Analysis and applications","author":"Li","year":"2003"},{"key":"ref13","article-title":"A reinforcement learning (Nash-R) algorithm for average reward irreducible stochastic games","author":"Li","year":"2007","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/070699652"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1516512.1516516"},{"key":"ref16","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Littman","year":"2001"},{"key":"ref18","first-page":"1371","article-title":"Two-timescale algorithms for learning Nash equilibria in general-sum stochastic games","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Prasad","year":"2015"},{"key":"ref19","first-page":"232","article-title":"Learning Nash equilibrium for general-sum Markov games from batch data","volume-title":"Proc. Artif. Intell. Statist.","author":"Prolat","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref21","article-title":"Decentralized Q-learning in zero-sum Markov games","volume":"34","author":"Sayin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Efficient exploration of zero-sum stochastic games","volume-title":"AAAI Workshop Reinforcement Learn. Games","author":"Martin","year":"2021"},{"key":"ref23","article-title":"Independent learning in stochastic games","volume-title":"Int. Congr. Mathematicians.","author":"Ozdaglar","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134045"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(02)00874-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-9352-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1984.1056894"},{"key":"ref28","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","volume":"48","author":"Borkar","year":"2009"},{"key":"ref29","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"key":"ref30","first-page":"2144","article-title":"Finite time analysis of linear two-timescale stochastic approximation with Markovian noise","volume-title":"Proc. Conf. Learn. Theory","author":"Kaledin","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2307\/3617665"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/81.754845"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref35","article-title":"A reinforcement learning approach for dynamic information flow tracking games for detecting advanced persistent threats","author":"Sahabandu","year":"2020"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10736196\/10535739-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10736196\/10535739.pdf?arnumber=10535739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:49:10Z","timestamp":1735847350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10535739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":35,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3403693","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}