{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:59:17Z","timestamp":1729619957113,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/ssci.2017.8280949","type":"proceedings-article","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T21:44:37Z","timestamp":1518039877000},"page":"1-6","source":"Crossref","is-referenced-by-count":17,"title":["Cooperative reinforcement learning for multiple units combat in starCraft"],"prefix":"10.1109","author":[{"given":"Kun","family":"Shao","sequence":"first","affiliation":[]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2478"},{"key":"ref11","article-title":"Episodic exploration for deep deterministic policies: An application to StarCraft microman-agement tasks","author":"usunier","year":"2017","journal-title":"International Conference on Learning Representations"},{"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":"2012","journal-title":"Proc AI Interactive Digit Entertain 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":"2012","journal-title":"Proc AI Interactive Digit Entertain Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2371316.2371324"},{"key":"ref17","first-page":"402","article-title":"Applying reinforcement learning to small scale combat in the real-time strategy game StarCraft: Broodwar","author":"wender","year":"2012","journal-title":"IEEE Conference on Computational Intelligence and Games"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"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","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref7","article-title":"Safe and nested subgame solving for imperfect-information games","author":"brown","year":"2017","journal-title":"AAAI Workshop on Computer Poker and Imperfect Information Games"},{"key":"ref2","first-page":"1","article-title":"Deep reinforcement learning with experience replay based on SARSA","author":"zhao","year":"2017","journal-title":"IEEE Symposium Series on Computational Intelligence"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FOCI.2013.6602463"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"journal-title":"Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games","year":"2017","author":"peng","key":"ref20"},{"journal-title":"Counterfactual multi-agent policy gradients","year":"2017","author":"foerster","key":"ref22"},{"key":"ref21","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref23"},{"key":"ref26","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"}],"event":{"name":"2017 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2017,11,27]]},"location":"Honolulu, HI","end":{"date-parts":[[2017,12,1]]}},"container-title":["2017 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8267146\/8280782\/08280949.pdf?arnumber=8280949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T14:21:59Z","timestamp":1570717319000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8280949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ssci.2017.8280949","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}