{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T11:46:15Z","timestamp":1654170375296},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T00:00:00Z","timestamp":1648684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T00:00:00Z","timestamp":1648684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Queueing Syst"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11134-022-09772-9","type":"journal-article","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T08:04:41Z","timestamp":1648713881000},"page":"513-515","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to cooperate in agent-based control of queueing networks"],"prefix":"10.1007","volume":"100","author":[{"given":"Vivek S.","family":"Borkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,31]]},"reference":[{"key":"9772_CR1","unstructured":"Abernethy, J., Bartlett, P.\u00a0L., Hazan, E.: Blackwell approachability and no-regret learning are equivalent. In Proceedings of the 24th Annual Conference on Learning Theory, pages 27\u201346. PMLR (2011)"},{"key":"9772_CR2","volume-title":"The Complexity of Cooperation","author":"R Axelrod","year":"1997","unstructured":"Axelrod, R.: The Complexity of Cooperation. Princeton University Press, NJ (1997)"},{"key":"9772_CR3","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control, vol. I and II (4th ed.). Athena Scientific, 2017\/2012"},{"key":"9772_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2140\/pjm.1956.6.1","volume":"6","author":"D Blackwell","year":"1956","unstructured":"Blackwell, D.: An analog of the minimax theorem for vector payoffs. Pac. J. Math. 6, 1\u20138 (1956)","journal-title":"Pac. J. Math."},{"key":"9772_CR5","doi-asserted-by":"publisher","DOI":"10.1017\/9781108380690","volume-title":"Data-driven Science and Engineering: Machine Learning, Dynamical Systems, and Control","author":"SL Brunton","year":"2019","unstructured":"Brunton, S.L., Kutz, J.N.: Data-driven Science and Engineering: Machine Learning, Dynamical Systems, and Control. Cambridge University Press, Cambridge (2019)"},{"key":"9772_CR6","doi-asserted-by":"publisher","first-page":"571","DOI":"10.2307\/2938191","volume":"58","author":"VP Crawford","year":"1990","unstructured":"Crawford, V.P., Haller, H.: Learning how to cooperate: Optimal play in repeated coordination games. Econometrica: J. Econometric Soc. 58, 571\u2013595 (1990)","journal-title":"Econometrica: J. Econometric Soc."},{"key":"9772_CR7","unstructured":"Dong, S., van Roy, B., Zhou, Z.: Simple agent, complex environment: Efficient reinforcement learning with agent state. arXiv preprint arXiv:2102.05261, (2021)"},{"key":"9772_CR8","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/0005-1098(76)90006-6","volume":"12","author":"BA Francis","year":"1976","unstructured":"Francis, B.A., Wonham, W.M.: The internal model principle in control theory. Automatica 12, 457\u2013465 (1976)","journal-title":"Automatica"},{"key":"9772_CR9","doi-asserted-by":"crossref","unstructured":"Levy, Y.J.: Discounted stochastic games with no stationary Nash equilibrium: two examples (corrigendum, with A. McLennan, in Econometrica 83(3), 1237\u20131252 (2015)). Econometrica 81, 1973\u20132007 (2013)","DOI":"10.3982\/ECTA12183"},{"key":"9772_CR10","unstructured":"Lu, X., van Roy, B., Dwaracherla, V., Ibrahimi, M., Osband, I., Wen, Z.: Reinforcement learning, bit by bit. arXiv preprint arXiv:2103.04047, (2021)"},{"key":"9772_CR11","doi-asserted-by":"crossref","unstructured":"Menache, I., Ozdaglar, A.: Network Games: Theory, Models, and Dynamics. Synthesis Lectures on Communication Networks. Morgan & Claypool Publishers, (2011)","DOI":"10.2200\/S00330ED1V01Y201101CNT009"},{"key":"9772_CR12","volume-title":"SuperCooperators","author":"MA Nowak","year":"2011","unstructured":"Nowak, M.A., Highfield, R.: SuperCooperators. Free Press, Mumbai (2011)"},{"key":"9772_CR13","first-page":"493","volume":"69","author":"H Simon","year":"1979","unstructured":"Simon, H.: Rational decision making in business organizations. Am. Econ. Rev. 69, 493\u2013513 (1979)","journal-title":"Am. Econ. Rev."},{"key":"9772_CR14","doi-asserted-by":"crossref","unstructured":"Walton, N., Xu, K.: Learning and information in stochastic networks and queues. arXiv preprint arXiv:2105.08769, (2021)","DOI":"10.1287\/educ.2021.0235"},{"key":"9772_CR15","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199269181.001.0001","volume-title":"Strategic Learning and its Limits","author":"H Young","year":"2004","unstructured":"Young, H.: Strategic Learning and its Limits. Oxford University Press, Oxford (2004)"},{"key":"9772_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1287\/moor.1070.0279","volume":"33","author":"H Yu","year":"2008","unstructured":"Yu, H., Bertsekas, D.: On near optimality of the set of finite-state controllers for average cost POMDP. Math. Oper. Res. 33, 1\u201311 (2008)","journal-title":"Math. Oper. Res."}],"container-title":["Queueing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11134-022-09772-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11134-022-09772-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11134-022-09772-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T11:26:13Z","timestamp":1654169173000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11134-022-09772-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,31]]},"references-count":16,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["9772"],"URL":"https:\/\/doi.org\/10.1007\/s11134-022-09772-9","relation":{},"ISSN":["0257-0130","1572-9443"],"issn-type":[{"value":"0257-0130","type":"print"},{"value":"1572-9443","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,31]]},"assertion":[{"value":"2 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}