{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:09:35Z","timestamp":1784905775753,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,2,1]],"date-time":"2019-02-01T00:00:00Z","timestamp":1548979200000},"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":["61573353"],"award-info":[{"award-number":["61573353"]}],"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":["61603382"],"award-info":[{"award-number":["61603382"]}],"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":["61533017"],"award-info":[{"award-number":["61533017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1109\/tetci.2018.2823329","type":"journal-article","created":{"date-parts":[[2018,4,27]],"date-time":"2018-04-27T19:01:33Z","timestamp":1524855693000},"page":"73-84","source":"Crossref","is-referenced-by-count":147,"title":["StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0965-4302","authenticated-orcid":false,"given":"Kun","family":"Shao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","article-title":"Prioritized experience replay","author":"schaul","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref31","first-page":"1529","article-title":"Recent progress of deep reinforcement learning: From AlphaGo to AlphaGo Zero","volume":"34","author":"tang","year":"2017","journal-title":"Control Theory Appl"},{"key":"ref30","first-page":"701","article-title":"Review of deep reinforcement learning and discussions on the development of computer Go","volume":"33","author":"zhao","year":"2016","journal-title":"Control Theory Appl"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966065"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"0"},{"key":"ref34","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref62","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"ref63","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2531680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2614002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2561300"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref20","article-title":"Episodic exploration for deep deterministic policies: An application to StarCraft micromanagement tasks","author":"usunier","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref21","article-title":"Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games","author":"peng","year":"2017","journal-title":"arXiv 1703 10069"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref23","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2769104"},{"key":"ref59","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc Conf Artif Intell Statist"},{"key":"ref58","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref57","article-title":"Learning to reinforcement learn","author":"wang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.64"},{"key":"ref55","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1038\/nature20101","article-title":"Hybrid computing using a neural network with dynamic external memory","volume":"538","author":"graves","year":"2016","journal-title":"Nature"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref52","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2478"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280949"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2414447"},{"key":"ref13","first-page":"31","article-title":"Kiting in RTS games using influence maps","author":"uriarte","year":"0","journal-title":"Proc Artif Intell Interactive Digit Entertainment Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2487743"},{"key":"ref15","first-page":"2","article-title":"Incorporating search algorithms into RTS game agents","author":"churchill","year":"0","journal-title":"Proc Artif Intell Interactive Digit Entertainment Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2371316.2371324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033442"},{"key":"ref18","first-page":"402","article-title":"Applying reinforcement learning to small scale combat in the real-time strategy game StarCraft: Broodwar","author":"wender","year":"0","journal-title":"Proc IEEE Conf Comput Intell Games"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/YAC.2016.7804906"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.032"},{"key":"ref6","first-page":"1","article-title":"Deep reinforcement learning with experience replay based on SARSA","author":"zhao","year":"0","journal-title":"Proc IEEE Symp Series Comput Intell"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1126\/science.aam6960","article-title":"Deepstack: Expert-level artificial intelligence in heads-up no-limit poker","volume":"356","author":"moravik","year":"2017","journal-title":"Science"},{"key":"ref49","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"jayesh","year":"0","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FOCI.2013.6602463"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref45","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"ming","year":"0","journal-title":"Proc 10th Int Conf Mach Learn"},{"key":"ref48","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"marc","year":"0","journal-title":"arXiv 1711 00832"},{"key":"ref47","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref43","first-page":"2746","article-title":"Embed to control: a locally linear latent dynamics model for control from raw images","author":"watter","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/8620575\/08351991.pdf?arnumber=8351991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:13Z","timestamp":1657746493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8351991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2018.2823329","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}