{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:29:01Z","timestamp":1760171341985,"version":"3.40.5"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:00:00Z","timestamp":1736467200000},"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":[[2025,1,10]]},"DOI":"10.1109\/ccnc54725.2025.10976107","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:52:06Z","timestamp":1746467526000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["MARS: Multi-Agent Deep Reinforcement Learning for Complex Environment Exploration"],"prefix":"10.1109","author":[{"given":"Francesco","family":"Gervino","sequence":"first","affiliation":[{"name":"Politecnico di Torino,Department of Control and Computer Engineering,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Eirale","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Chiaberge","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessio","family":"Sacco","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Control and Computer Engineering,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guido","family":"Marchetto","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Control and Computer Engineering,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio","family":"Casetti","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Control and Computer Engineering,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proceedings of The 33rd International Con-ference on Machine Learning (ICML)","author":"Mnih"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/504729.504754"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref5","article-title":"Learning to navigate in complex environments","author":"Mirowski","year":"2016","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3059647"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3215669"},{"key":"ref9","article-title":"Neural slam: Learning to explore with external memory","author":"Zhang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Plugo: a vlc systematic perspective of large-scale indoor localization","author":"Liang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2014.6932662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041446"},{"article-title":"Fastslam: A factored solution to the simultaneous localization and mapping problem","volume-title":"Proc. of AAAI02","author":"Montemerlo","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2010.939925"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s40638-016-0055-x"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS57453.2023.10226167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref21","article-title":"Double q-learning","volume":"23","author":"Hasselt","year":"2010","journal-title":"Advances in neural information pro-cessing systems"}],"event":{"name":"2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)","start":{"date-parts":[[2025,1,10]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2025,1,13]]}},"container-title":["2025 IEEE 22nd Consumer Communications & Networking Conference (CCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10975854\/10975830\/10976107.pdf?arnumber=10976107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T04:50:43Z","timestamp":1746507043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,10]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ccnc54725.2025.10976107","relation":{},"subject":[],"published":{"date-parts":[[2025,1,10]]}}}