{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:45:55Z","timestamp":1775144755312,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tnnls.2024.3382480","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T18:32:31Z","timestamp":1712687551000},"page":"5535-5546","source":"Crossref","is-referenced-by-count":4,"title":["Graph Exploration for Effective Multiagent Q-Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-9249","authenticated-orcid":false,"given":"Ainur","family":"Zhaikhan","sequence":"first","affiliation":[{"name":"Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5125-5519","authenticated-orcid":false,"given":"Ali H.","family":"Sayed","sequence":"additional","affiliation":[{"name":"Adaptive Systems Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref2","article-title":"A survey of exploration methods in reinforcement learning","author":"Amin","year":"2021","journal-title":"arXiv:2109.00157"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/9781009218245"},{"issue":"1","key":"ref4","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Rashid"},{"key":"ref6","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref7","article-title":"Mean field multi-agent reinforcement learning","author":"Yang","year":"2018","journal-title":"arXiv:1802.05438"},{"key":"ref8","article-title":"ISL: A novel approach for deep exploration","author":"Cassano","year":"2019","journal-title":"arXiv:1909.06293"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867146"},{"key":"ref10","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Liu"},{"key":"ref11","article-title":"Provably efficient cooperative multi-agent reinforcement learning with function approximation","author":"Dubey","year":"2021","journal-title":"arXiv:2103.04972"},{"key":"ref12","article-title":"Temporal difference uncertainties as a signal for exploration","author":"Flennerhag","year":"2020","journal-title":"arXiv:2010.02255"},{"key":"ref13","first-page":"1037","article-title":"Smart exploration in reinforcement learning using absolute temporal difference errors","volume-title":"Proc. Int. Conf. Auto. Agents Multi-Agent Syst.","author":"Gehring"},{"key":"ref14","first-page":"487","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","volume-title":"Readings in Agents","author":"Tan","year":"1997"},{"key":"ref15","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref16","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref17","first-page":"3246","article-title":"Learning infinite-horizon average-reward Markov decision process with constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Chen"},{"key":"ref18","first-page":"3149","article-title":"On the sample complexity of learning infinite-horizon discounted linear kernel MDPs","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Chen"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2023.111030","article-title":"Distributed output data-driven optimal robust synchronization of heterogeneous multi-agent systems","volume":"153","author":"Chen","year":"2023","journal-title":"Automatica"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2020.109149","article-title":"Cooperative adaptive optimal output regulation of nonlinear discrete-time multi-agent systems","volume":"121","author":"Jiang","year":"2020","journal-title":"Automatica"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2020.109081","article-title":"Off-policy learning for adaptive optimal output synchronization of heterogeneous multi-agent systems","volume":"119","author":"Chen","year":"2020","journal-title":"Automatica"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146201"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3262921"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3326867"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44581-1_39"},{"key":"ref30","first-page":"1","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"11","author":"Kearns"},{"key":"ref31","article-title":"Ensemble bootstrapping for Q-learning","author":"Peer","year":"2021","journal-title":"arXiv:2103.00445"},{"key":"ref32","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"29","author":"Osband"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.4208\/jml.230105"},{"key":"ref34","first-page":"13903","article-title":"On function approximation in reinforcement learning: Optimism in the face of large state spaces","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref35","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref38","first-page":"1","article-title":"The asymptotic convergence-rate of Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"10","author":"Szepesv\u00e1ri"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10908444\/10495205.pdf?arnumber=10495205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:39:44Z","timestamp":1741027184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10495205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":38,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3382480","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}