{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T14:31:08Z","timestamp":1773930668215,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS 1947418"],"award-info":[{"award-number":["CNS 1947418"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS 1947419"],"award-info":[{"award-number":["ECCS 1947419"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/tnnls.2020.3042943","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T20:33:06Z","timestamp":1608669186000},"page":"1584-1593","source":"Crossref","is-referenced-by-count":20,"title":["Semicentralized Deep Deterministic Policy Gradient in Cooperative StarCraft Games"],"prefix":"10.1109","volume":"33","author":[{"given":"Dong","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, University of North Texas, Denton, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8367-0215","authenticated-orcid":false,"given":"Xiangnan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref3","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017","journal-title":"arXiv:1701.07274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref6","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref7","article-title":"Dueling network architectures for deep reinforcement learning","author":"Wang","year":"2015","journal-title":"arXiv:1511.06581"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref9","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref10","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref11","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref12","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"ref19","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref20","article-title":"Stochastic neural networks for hierarchical reinforcement learning","author":"Florensa","year":"2017","journal-title":"arXiv:1704.03012"},{"key":"ref21","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref22","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Vezhnevets"},{"key":"ref23","first-page":"1534","article-title":"Real-time strategy games: A new AI research challenge","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Buro"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FOCI.2013.6602463"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63519-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref28","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2419"},{"key":"ref32","volume-title":"BWAPI: Brood War API, an API for Interacting With starcraft: Broodwar (1.16.1)","author":"Heinermann","year":"2015"},{"key":"ref33","article-title":"TorchCraft: A library for machine learning research on real-time strategy games","author":"Synnaeve","year":"2016","journal-title":"arXiv:1611.00625"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08234-9_18-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5230"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848109"},{"key":"ref38","article-title":"Episodic exploration for deep deterministic policies: An application to StarCraft micromanagement tasks","author":"Usunier","year":"2016","journal-title":"arXiv:1609.02993"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref40","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017","journal-title":"arXiv:1703.10069"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref42","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9749160\/9302688-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9749160\/09302688.pdf?arnumber=9302688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:46:50Z","timestamp":1704840410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9302688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":43,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3042943","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}