{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T14:17:25Z","timestamp":1783433845444,"version":"3.54.6"},"reference-count":34,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276097"],"award-info":[{"award-number":["62276097"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372174"],"award-info":[{"award-number":["62372174"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62136003"],"award-info":[{"award-number":["62136003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.future.2026.108663","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T23:59:22Z","timestamp":1781135962000},"page":"108663","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["EntShare: Adaptive entropy balancing for multi-agent reinforcement learning with selective knowledge sharing"],"prefix":"10.1016","volume":"185","author":[{"given":"Jiarou","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6667-7222","authenticated-orcid":false,"given":"Suhang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-3440","authenticated-orcid":false,"given":"Xiang","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1899-1135","authenticated-orcid":false,"given":"Huiqun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.future.2026.108663_b1","series-title":"Proc. Int. Joint Conf. Neural Networks","first-page":"1","article-title":"Multi-agent connected autonomous driving using deep reinforcement learning","author":"Palanisamy","year":"2020"},{"issue":"6","key":"10.1016\/j.future.2026.108663_b2","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: A survey","volume":"23","author":"Kiran","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.future.2026.108663_b3","doi-asserted-by":"crossref","first-page":"8190","DOI":"10.1109\/TIV.2024.3408257","article-title":"Multiagent reinforcement learning: Methods, trustworthiness, applications in intelligent vehicles, and challenges","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.future.2026.108663_b4","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Toward efficient multi-agent exploration with trajectory entropy maximization","author":"Li","year":"2025"},{"key":"10.1016\/j.future.2026.108663_b5","series-title":"Proc. Int. Conf. Autonomous Agents and Multiagent Systems","first-page":"2253","article-title":"Adaptive episode length adjustment for multi-agent reinforcement learning","author":"Yoo","year":"2025"},{"key":"10.1016\/j.future.2026.108663_b6","series-title":"Proc. Int. Conf. Autonomous Agents and Multiagent Systems","first-page":"2373","article-title":"Offline-to-online multi-agent reinforcement learning with offline value function memory and sequential exploration","author":"Zhong","year":"2025"},{"key":"10.1016\/j.future.2026.108663_b7","series-title":"Proc. Int. Conf. Autonomous Agents and Multiagent Systems","first-page":"2146","article-title":"A very condensed survey and critique of multiagent deep reinforcement learning","author":"Hernandez-Leal","year":"2020"},{"key":"10.1016\/j.future.2026.108663_b8","series-title":"Proc. Int. Conf. Machine Learning","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"Foerster","year":"2017"},{"key":"10.1016\/j.future.2026.108663_b9","series-title":"Proc. Int. Conf. Machine Learning","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2019"},{"key":"10.1016\/j.future.2026.108663_b10","series-title":"Advances in Neural Information Processing Systems","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"Foerster","year":"2016"},{"key":"10.1016\/j.future.2026.108663_b11","series-title":"Proc. Int. Conf. Autonomous Agents and Multiagent Systems","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"Sunehag","year":"2018"},{"key":"10.1016\/j.future.2026.108663_b12","first-page":"178:1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.future.2026.108663_b13","series-title":"Advances in Neural Information Processing Systems","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","author":"Mahajan","year":"2019"},{"key":"10.1016\/j.future.2026.108663_b14","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"10.1016\/j.future.2026.108663_b15","series-title":"Advances in Neural Information Processing Systems","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017"},{"key":"10.1016\/j.future.2026.108663_b16","series-title":"Proc. AAAI Conf. Artificial Intelligence","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018"},{"key":"10.1016\/j.future.2026.108663_b17","series-title":"Advances in Neural Information Processing Systems","first-page":"2244","article-title":"Learning multi-agent communication with backpropagation","author":"Sukhbaatar","year":"2016"},{"key":"10.1016\/j.future.2026.108663_b18","series-title":"Proc. AAAI Conf. Artificial Intelligence","first-page":"7211","article-title":"Multi-agent game abstraction via graph attention neural network","author":"Liu","year":"2020"},{"key":"10.1016\/j.future.2026.108663_b19","series-title":"Proc. IEEE\/RSJ Int. Conf. Intelligent Robots and Systems","first-page":"8193","article-title":"Policy distillation and value matching in multi-agent reinforcement learning","author":"Wadhwania","year":"2019"},{"key":"10.1016\/j.future.2026.108663_b20","series-title":"Advances in Neural Information Processing Systems","article-title":"Shared experience actor-critic for multi-agent reinforcement learning","author":"Christianos","year":"2020"},{"issue":"20","key":"10.1016\/j.future.2026.108663_b21","doi-asserted-by":"crossref","first-page":"4334","DOI":"10.3390\/math11204334","article-title":"Workflow scheduling scheme for optimized reliability and end-to-end delay control in cloud computing using AI-based modeling","volume":"11","author":"Khaleel","year":"2023","journal-title":"Mathematics"},{"issue":"16","key":"10.1016\/j.future.2026.108663_b22","doi-asserted-by":"crossref","first-page":"3563","DOI":"10.3390\/math11163563","article-title":"A hybrid many-objective optimization algorithm for job scheduling in cloud computing based on merge-and-split theory","volume":"11","author":"Khaleel","year":"2023","journal-title":"Mathematics"},{"key":"10.1016\/j.future.2026.108663_b23","series-title":"Proc. Int. Conf. Autonomous Agents and Multiagent Systems","first-page":"1100","article-title":"Simultaneously learning and advising in multi-agent reinforcement learning","author":"da Silva","year":"2017"},{"key":"10.1016\/j.future.2026.108663_b24","series-title":"Proc. AAAI Conf. Artificial Intelligence","first-page":"17299","article-title":"Cautiously-optimistic knowledge sharing for cooperative multi-agent reinforcement learning","author":"Ba","year":"2024"},{"key":"10.1016\/j.future.2026.108663_b25","series-title":"Proc. Int. Conf. Machine Learning","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.future.2026.108663_b26","series-title":"The exploration-exploitation dilemma revisited: An entropy perspective","author":"Yan","year":"2024"},{"key":"10.1016\/j.future.2026.108663_b27","series-title":"Proc. Int. Conf. Machine Learning","first-page":"16829","article-title":"An adaptive entropy-regularization framework for multi-agent reinforcement learning","author":"Kim","year":"2023"},{"key":"10.1016\/j.future.2026.108663_b28","series-title":"Proc. Genetic and Evolutionary Computation Conf.","first-page":"212","article-title":"Entropy-based local fitnesses for evolutionary multi-agent systems","author":"Aydeniz","year":"2022"},{"issue":"3","key":"10.1016\/j.future.2026.108663_b29","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/j.future.2026.108663_b30","series-title":"Computers in Cardiology","first-page":"705","article-title":"Multiscale entropy analysis of complex heart rate dynamics","author":"Costa","year":"2003"},{"key":"10.1016\/j.future.2026.108663_b31","series-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.future.2026.108663_b32","series-title":"Proc. Int. Conf. Machine Learning","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","author":"Ahmed","year":"2019"},{"key":"10.1016\/j.future.2026.108663_b33","article-title":"Energy-latency trade-off analysis for scientific workflow in cloud environments: The role of processor utilization ratio and mean grey wolf optimizer","volume":"50","author":"Khaleel","year":"2024","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"10.1016\/j.future.2026.108663_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2021.103653","article-title":"Exploration-exploitation in multi-agent learning: Catastrophe theory meets game theory","volume":"304","author":"Leonardos","year":"2022","journal-title":"Artificial Intelligence"}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26002979?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X26002979?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T13:44:48Z","timestamp":1783431888000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X26002979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":34,"alternative-id":["S0167739X26002979"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108663","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"EntShare: Adaptive entropy balancing for multi-agent reinforcement learning with selective knowledge sharing","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108663","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108663"}}