{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T06:20:11Z","timestamp":1770531611312,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236007"],"award-info":[{"award-number":["62236007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tcds.2023.3339131","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T19:55:11Z","timestamp":1702583711000},"page":"1161-1171","source":"Crossref","is-referenced-by-count":2,"title":["Entropy Enhanced Multiagent Coordination Based on Hierarchical Graph Learning for Continuous Action Space"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3435-2851","authenticated-orcid":false,"given":"Yining","family":"Chen","sequence":"first","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4869-5135","authenticated-orcid":false,"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3330-4978","authenticated-orcid":false,"given":"Guanghua","family":"Song","sequence":"additional","affiliation":[{"name":"School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5180-1137","authenticated-orcid":false,"given":"Xiaohong","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"issue":"1","key":"ref2","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"J. Mach. Learn. Res.","volume":"21","author":"Rashid","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2186833"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3185975"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref9","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Fujimoto","year":"2018"},{"key":"ref10","article-title":"Distributed distributional deterministic policy gradients","author":"Barth-Maron","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Mnih","year":"2016"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Schulman","year":"2015"},{"key":"ref14","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref16","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. 23rd AAAI Conf. Artif. Intell.","volume":"8","author":"Ziebart","year":"2008"},{"key":"ref17","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Haarnoja","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","first-page":"1","article-title":"Learning continuous control policies by stochastic value gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Heess","year":"2015"},{"key":"ref22","first-page":"10","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref23","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3092715"},{"key":"ref25","first-page":"1","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Osband","year":"2016"},{"key":"ref26","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3110959"},{"key":"ref29","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref30","first-page":"9","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Iqbal","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.093"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref34","article-title":"Graph convolutional reinforcement learning","author":"Jiang","year":"2018"},{"key":"ref35","article-title":"Graph attention networks","author":"Velickovi\u0107","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref37","first-page":"964","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Niu","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3197918"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3323987"},{"key":"ref41","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/e24040563"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200073"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/e24050638"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3146881"},{"key":"ref48","volume-title":"A Quantitative Measure of Fairness and Discrimination","author":"Jain","year":"1984"},{"issue":"3\u20134","key":"ref49","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref51","article-title":"How attentive are graph attention networks?\u201d","author":"Brody","year":"2021"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10552653\/10360442.pdf?arnumber=10360442","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:08:36Z","timestamp":1719349716000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360442\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":51,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3339131","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}