{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:12:14Z","timestamp":1778616734881,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["2640\/20"],"award-info":[{"award-number":["2640\/20"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3430392","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T17:38:38Z","timestamp":1721324318000},"page":"130444-130459","source":"Crossref","is-referenced-by-count":6,"title":["Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing"],"prefix":"10.1109","volume":"12","author":[{"given":"Hadar","family":"Szostak","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Be’er Sheva, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0532-009X","authenticated-orcid":false,"given":"Kobi","family":"Cohen","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Be’er Sheva, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton49937.2022.9929423"},{"key":"ref2","volume-title":"Sequential Analysis","volume":"15805","author":"Wald","year":"1947"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177706205"},{"key":"ref4","article-title":"Theory and applications of the sequential design of experiments, k-actions and infinitely many experiments. Part I. Theory","author":"Bessler","year":"1960"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2261188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/07474946.2014.961864"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1144"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2261279"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","first-page":"1","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Foerster"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref12","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8636086"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8635928"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013223"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103589"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154275"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2967566"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0890-5401(87)90038-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2014.2367358"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7403046"},{"key":"ref22","first-page":"1","article-title":"Deep reinforcement learning for active hypothesis testing with heterogeneous agents and cost constraints","volume":"1","author":"Stamatelis","year":"2023","journal-title":"TechRxiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3087410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2626578"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2023.3310353"},{"key":"ref27","volume-title":"Code for Paper: Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2159038"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2012.101712.110599"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2253351"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2332982"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2387857"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2416674"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2602802"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2593772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2775614"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2866257"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2883014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849555"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2918981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014619"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2971438"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2020.3041780"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3106587"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3136810"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3177142"},{"key":"ref47","article-title":"Joint sequential detection and isolation for dependent data streams","author":"Chaudhuri","year":"2022","journal-title":"arXiv:2207.00120"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3198166"},{"key":"ref49","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref50","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref51","first-page":"1","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3250106"},{"key":"ref53","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"Liang","year":"2017","journal-title":"arXiv:1712.09381"},{"key":"ref54","first-page":"3053","article-title":"RLlib: Abstractions for distributed reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref55","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013541"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3125282"},{"key":"ref58","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10602508.pdf?arnumber=10602508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T04:54:59Z","timestamp":1727240099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10602508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3430392","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}