{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T17:03:46Z","timestamp":1775581426754,"version":"3.50.1"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Institute of Health","award":["1R21EB032480-01"],"award-info":[{"award-number":["1R21EB032480-01"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2311969"],"award-info":[{"award-number":["IIS-2311969"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2202395"],"award-info":[{"award-number":["IIS-2202395"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ARMY Research Laboratory","award":["W911NF2320179"],"award-info":[{"award-number":["W911NF2320179"]}]},{"DOI":"10.13039\/100000183","name":"ARMY Research Office","doi-asserted-by":"publisher","award":["W911NF2110299"],"award-info":[{"award-number":["W911NF2110299"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-23-1-2850"],"award-info":[{"award-number":["N00014-23-1-2850"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Biol. Bioinform."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tcbbio.2025.3633151","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:40:23Z","timestamp":1763404823000},"page":"3524-3537","source":"Crossref","is-referenced-by-count":1,"title":["Decentralized Reinforcement Learning for Asymmetric Gene Network Interventions"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4317-0216","authenticated-orcid":false,"given":"Seyed Hamid","family":"Hosseini","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9570-9909","authenticated-orcid":false,"given":"Mahdi","family":"Imani","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2024.3424400"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.928089"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2022.3173969"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fcteg.2022.1017256"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btt242"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3070307"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.matcom.2020.04.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1176935118790247"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2021.3133608"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/ACC55779.2023.10155867"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3229054"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5909"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2018.04.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-65351-4_29"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA60707.2024.10666558"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2014.02.011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.873740"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.3017155"},{"key":"ref19","article-title":"QMDP-Net: Deep learning for planning under partial observability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Karkus"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC63710.2025.11107606"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120440"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495613"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2024.3383814"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3398712"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/21642583.2024.2329260"},{"key":"ref27","article-title":"Accelerating proximal policy optimization learning using task prediction for solving environments with delayed rewards","author":"Ahmad","year":"2024"},{"key":"ref28","first-page":"11602","article-title":"Policy optimization provably converges to Nash equilibria in zero-sum linear quadratic games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3208611"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2933396"},{"key":"ref31","article-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning","author":"Amato","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref33","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref34","first-page":"25779","article-title":"When are offline two-player zero-sum Markov games solvable?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cui"},{"key":"ref35","first-page":"11987","article-title":"Learning in two-player zero-sum partially observable Markov games with perfect recall","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kozuno"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/18.10.1319"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1117\/12.281504"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1006\/game.1995.1034"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3302656"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30440-3_29"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304126"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.03.003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2024.09.018"},{"key":"ref45","volume-title":"Theory of Games and Economic Behavior","author":"Rubinstein","year":"2007"},{"key":"ref46","volume-title":"Linear Programming","author":"Chvtal","year":"1983"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref51","article-title":"More centralized training, still decentralized execution: Multi-agent conditional policy factorization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref52","article-title":"Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management","author":"Saifullah","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09838-1"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref56","first-page":"32375","article-title":"A theoretical justification for asymmetric actor-critic algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lambrechts"},{"key":"ref57","first-page":"1166","article-title":"Model-based multi-agent RL in zero-sum Markov games with near-optimal sample complexity","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.034"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s40435-025-01756-w"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3704"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.804686"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/nrc2604"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-018-0543-y"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2614798"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2011.107"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1142\/S0218339012400049"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/S1535-6108(02)00045-4"}],"container-title":["IEEE Transactions on Computational Biology and Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/10723156\/11296745\/11250698-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723156\/11296745\/11250698.pdf?arnumber=11250698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:45:02Z","timestamp":1765478702000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11250698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcbbio.2025.3633151","relation":{},"ISSN":["2998-4165"],"issn-type":[{"value":"2998-4165","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}