{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T04:01:20Z","timestamp":1751774480666,"version":"3.41.0"},"publisher-location":"Cham","reference-count":10,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319938172"},{"type":"electronic","value":"9783319938189"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-93818-9_4","type":"book-chapter","created":{"date-parts":[[2018,6,15]],"date-time":"2018-06-15T18:47:06Z","timestamp":1529088426000},"page":"36-42","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Real-Time Multiagent Strategy Learning Environment and Experimental Framework"],"prefix":"10.1007","author":[{"given":"Hongda","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Decai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liying","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,16]]},"reference":[{"issue":"4","key":"4_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TCIAIG.2013.2286295","volume":"5","author":"O Santiago","year":"2013","unstructured":"Santiago, O., Gabriel, S., Alberto, U.: A survey of real-time strategy game AI research and competition in StarCraft. IEEE Trans. Comput. Intell. AI Games 5(4), 293\u2013309 (2013)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"4_CR2","unstructured":"Marc, G.B., Yavar, N., Joel, V., Michael, B.: The arcade learning environment: an evaluation platform for general agents. In: 24th International Joint Conference on Artificial Intelligence, pp. 4148\u20134152 (2015)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Stefan, W., Ian, W.: Applying reinforcement learning to small scale combat in the real-time strategy game StarCraft: Broodwar. In: 2012 IEEE Conference on Computational Intelligence and Games (CIG 2012), pp. 402\u2013408 (2012)","DOI":"10.1109\/CIG.2012.6374183"},{"issue":"5740","key":"4_CR4","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D.: Human-level control through deep reinforcement learning. Nature 518(5740), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"4_CR5","unstructured":"Sainbayar, S., Arthur, S., Gabriel, S., Soumith, C., Rob, F.: Mazebase: a sandbox for learning from games. https:\/\/arxiv.org\/abs\/1511.07401"},{"key":"4_CR6","unstructured":"Nicolas, U., Gabriel, S., Zeming, L., Soumith, C.: Episodic exploration for deep deterministic policies: an application to StarCraft micromanagement tasks. https:\/\/arxiv.org\/abs\/1609.02993"},{"key":"4_CR7","unstructured":"Peng, P., Ying, W., Yaodong, Y.: Multiagent bidirectionally-coordinated nets emergence of human-level coordination in learning to play StarCraft combat games. https:\/\/arxiv.org\/abs\/1703.10069"},{"key":"4_CR8","unstructured":"Jakob, N.F., Gregory, F., Triantafyllos, A.: Counterfactual multi-agent policy gradients. In: The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018), New Orleans (2018)"},{"key":"4_CR9","unstructured":"Oriol, V., Timo, E., Kevin, C.: StarCraft II: a new challenge for reinforcement learning. https:\/\/arxiv.org\/abs\/1708.04782"},{"key":"4_CR10","unstructured":"Marc, L., Vinicius, Z., Audrunas, G.: A unified game-theoretic approach to multiagent reinforcement learning. https:\/\/arxiv.org\/abs\/1711.00832"}],"container-title":["Lecture Notes in Computer Science","Advances in Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93818-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:30:33Z","timestamp":1751689833000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-93818-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319938172","9783319938189"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93818-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"16 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}