{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:05:02Z","timestamp":1760709902973,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T00:00:00Z","timestamp":1557964800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T00:00:00Z","timestamp":1557964800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Agence National de la Recherche","award":["ANR-13-BS01-0005"],"award-info":[{"award-number":["ANR-13-BS01-0005"]}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"crossref","award":["ANR-16-CE40-0002"],"award-info":[{"award-number":["ANR-16-CE40-0002"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1007\/s10994-019-05799-x","type":"journal-article","created":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T21:03:36Z","timestamp":1558040616000},"page":"1919-1949","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Asymptotically optimal algorithms for budgeted multiple play bandits"],"prefix":"10.1007","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9936-3236","authenticated-orcid":false,"given":"Alex","family":"Luedtke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emilie","family":"Kaufmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Chambaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,16]]},"reference":[{"key":"5799_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, S., & Devanur, N. R. (2014). Bandits with concave rewards and convex knapsacks. In Proceedings of the fifteenth ACM conference on Economics and computation (pp. 989\u20131006). ACM.","DOI":"10.1145\/2600057.2602844"},{"key":"5799_CR2","unstructured":"Agrawal, S., & Goyal, N. (2011). Analysis of thompson sampling for the multi-armed bandit problem. arXiv preprint arXiv:1111.1797 ."},{"key":"5799_CR3","unstructured":"Agrawal, S., & Goyal, N. (2012). Further optimal regret bounds for thompson sampling. arXiv preprint arXiv:1209.3353 ."},{"issue":"11","key":"5799_CR4","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/TAC.1987.1104491","volume":"32","author":"V Anantharam","year":"1987","unstructured":"Anantharam, V., Varaiya, P., & Walrand, J. (1987). Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: IID rewards. IEEE Transactions on Automatic Control, 32(11), 968\u2013976.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"5799_CR5","unstructured":"Audibert, J. -Y., Bubeck, S., & Lugosi, G. (2011). Minimax policies for combinatorial prediction games. arXiv preprint arXiv:1105.4871 ."},{"key":"5799_CR6","doi-asserted-by":"crossref","unstructured":"Badanidiyuru, A., Kleinberg, R., & Slivkins, A. (2013). Bandits with knapsacks. In 2013 IEEE 54th annual symposium on foundations of computer science (FOCS) (pp. 207\u2013216). IEEE.","DOI":"10.1109\/FOCS.2013.30"},{"issue":"2","key":"5799_CR7","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1006\/aama.1996.0007","volume":"17","author":"AN Burnetas","year":"1996","unstructured":"Burnetas, A. N., & Katehakis, M. (1996). Optimal adaptive policies for sequential allocation problems. Advances in Applied Mathematics, 17(2), 122\u2013142.","journal-title":"Advances in Applied Mathematics"},{"issue":"3","key":"5799_CR8","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.1214\/13-AOS1119","volume":"41","author":"O Capp\u00e9","year":"2013","unstructured":"Capp\u00e9, O., Garivier, A., Maillard, O. A., Munos, R., & Stoltz, G. (2013a). Kullback-leibler upper confidence bounds for optimal sequential allocation. The Annals of Statistics, 41(3), 1516\u20131541.","journal-title":"The Annals of Statistics"},{"key":"5799_CR9","doi-asserted-by":"publisher","unstructured":"Capp\u00e9, O., Garivier, A., Maillard, O. A., Munos, R., & Stoltz, G. (2013b). Supplement to \u201cKullback-Leibler upper confidence bounds for optimal sequential allocation\u201d. https:\/\/doi.org\/10.1214\/13-AOS1119SUPP .","DOI":"10.1214\/13-AOS1119SUPP"},{"key":"5799_CR10","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1016\/j.jcss.2012.01.001","volume":"78","author":"N Cesa-Bianchi","year":"2012","unstructured":"Cesa-Bianchi, N., & Lugosi, G. (2012). Combinatorial bandits. Journal of Computer and System Sciences, 78, 1404\u20131422.","journal-title":"Journal of Computer and System Sciences"},{"key":"5799_CR11","unstructured":"Chen, W., Wang, Y., & Yuan, Y. (2013). Combinatorial multi-armed bandit: General framework and applications. In Proceedings of the 30th international conference on machine learning (pp. 151\u2013159)."},{"key":"5799_CR12","doi-asserted-by":"crossref","unstructured":"Combes, R., Magureanu, S., Prouti\u00e8re, A., & Laroche, C. (2015a). Learning to rank: Regret lower bounds and efficient algorithms. In Proceedings of the 2015 ACM SIGMETRICS international conference on measurement and modeling of computer systems (pp. 231\u2013244).","DOI":"10.1145\/2796314.2745852"},{"key":"5799_CR13","unstructured":"Combes, R., Shahi, M. S. T. M., Proutiere, A., & Lelarge, M. (2015b). Combinatorial bandits revisited. In Advances in neural information processing systems (pp. 2107\u20132115)."},{"issue":"2","key":"5799_CR14","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1287\/opre.5.2.266","volume":"5","author":"GB Dantzig","year":"1957","unstructured":"Dantzig, G. B. (1957). Discrete-variable extremum problems. Operations Research, 5(2), 266\u2013288.","journal-title":"Operations Research"},{"key":"5799_CR15","unstructured":"Garivier, A., M\u00e9nard, P., & Stoltz, G. (2016). Explore first, exploit next: The true shape of regret in bandit problems. arXiv preprint arXiv:1602.07182 ."},{"issue":"2","key":"5799_CR16","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1111\/j.2517-6161.1979.tb01068.x","volume":"41","author":"JC Gittins","year":"1979","unstructured":"Gittins, J. C. (1979). Bandit processes and dynamic allocation indices. Journal of the Royal Statistical Society Series B, 41(2), 148\u2013177.","journal-title":"Journal of the Royal Statistical Society Series B"},{"key":"5799_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-2001-2_9","volume-title":"Reducibility among combinatorial problems","author":"RM Karp","year":"1972","unstructured":"Karp, R. M. (1972). Reducibility among combinatorial problems. New York, Berlin, Heidelberg: Springer."},{"key":"5799_CR18","doi-asserted-by":"crossref","unstructured":"Kaufmann, E., Korda, N., & Munos, R. (2012). Thompson sampling: An asymptotically optimal finite-time analysis. In Algorithmic learning theory (pp. 199\u2013213). Springer.","DOI":"10.1007\/978-3-642-34106-9_18"},{"key":"5799_CR19","unstructured":"Komiyama, J., Honda, J., & Nakagawa, H. (2015). Optimal regret analysis of thompson sampling in stochastic multi-armed bandit problem with multiple plays. arXiv preprint arXiv:1506.00779 ."},{"key":"5799_CR20","unstructured":"Korda, N., Kaufmann, E., & Munos, R. (2013). Thompson sampling for 1-dimensional exponential family bandits. In Advances in neural information processing systems (pp. 1448\u20131456)."},{"key":"5799_CR21","unstructured":"Kveton, B., Szepesv\u00e1ri, C., Wen, Z., & Ashkan, A. (2015a). Cascading bandits: Learning to rank in the cascade model. In Proceedings of the 32nd international conference on machine learning (pp. 767\u2013776)."},{"key":"5799_CR22","unstructured":"Kveton, B., Weng, Z., Ashkan, A., Hoda, E., & Eriksson, B. (2014). Matroid bandits: Fast combinatorial optimization with learning. In Uncertainty in artificial intelligence (UAI)."},{"key":"5799_CR23","unstructured":"Kveton, B., Zheng, W., Ashkan, A., & Szepesv\u00e1ri, C. (2015b). Combinatorial cascading bandits. In Advances in neural information processing systems (NIPS)."},{"key":"5799_CR24","unstructured":"Lagr\u00e9e, P., Vernade, C., & Capp\u00e9, O. (2016). Multiple-play bandits in the postition-based model. arXiv preprint arXiv:1606.02448 ."},{"key":"5799_CR25","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1214\/aos\/1176350495","volume":"15","author":"TL Lai","year":"1987","unstructured":"Lai, T. L. (1987). Adaptive treatment allocation and the multi-armed bandit problem. The Annals of Statistics, 15, 1091\u20131114.","journal-title":"The Annals of Statistics"},{"issue":"1","key":"5799_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/0196-8858(85)90002-8","volume":"6","author":"TL Lai","year":"1985","unstructured":"Lai, T. L., & Robbins, H. (1985). Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics, 6(1), 4\u201322.","journal-title":"Advances in Applied Mathematics"},{"key":"5799_CR27","doi-asserted-by":"crossref","unstructured":"Li, H., & Xia, Y. (2017). Infinitely many-armed bandits with budget constraints. In AAAI (pp. 2182\u20132188).","DOI":"10.1609\/aaai.v31i1.10881"},{"key":"5799_CR28","unstructured":"Luedtke, A., Kaufmann, E., & Chambaz, A. (2016). Asymptotically Optimal algorithms for multiple play bandits with partial feedback. arXiv preprint arXiv:1606.09388 ."},{"key":"5799_CR29","unstructured":"R Core Team. (2014). R: A language and environment for statistical computing. Retrieved July 1, 2016 from http:\/\/www.r-project.org\/ ."},{"issue":"5","key":"5799_CR30","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1090\/S0002-9904-1952-09620-8","volume":"58","author":"H Robbins","year":"1952","unstructured":"Robbins, H. (1952). Some aspects of the sequential design of experiments. Bulletin of the American Mathematical Society, 58(5), 527\u2013535.","journal-title":"Bulletin of the American Mathematical Society"},{"key":"5799_CR31","unstructured":"Sankararaman, K., & Slivkins, A. (2018). Combinatorial semi-bandits with knapsacks. In AISTATS."},{"issue":"3\/4","key":"5799_CR32","doi-asserted-by":"publisher","first-page":"285","DOI":"10.2307\/2332286","volume":"25","author":"WR Thompson","year":"1933","unstructured":"Thompson, W. R. (1933). On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 25(3\/4), 285\u2013294.","journal-title":"Biometrika"},{"key":"5799_CR33","unstructured":"Tran-Thanh, L., Chapman, A. C., Rogers, A., & Jennings, N. R. (2012). Knapsack based optimal policies for budget-limited multi-armed bandits. In AAAI."},{"key":"5799_CR34","unstructured":"Wen, Z., Kveton, B., & Ashkan, A. (2015). Efficient learning in large-scale combinatorial semi-bandits. In International conference on machine learning (ICML)."},{"key":"5799_CR35","unstructured":"Xia, Y., Ding, W., Zhang, X. -D., Yu, N., & Qin, T. (2016a). Budgeted bandit problems with continuous random costs. In Asian conference on machine learning (pp. 317\u2013332)."},{"key":"5799_CR36","unstructured":"Xia, Y., Li, H., Qin, T., Yu, N., & Liu, T. -Y. (2015). Thompson sampling for budgeted multi-armed bandits. In IJCAI (pp. 3960\u20133966)."},{"key":"5799_CR37","unstructured":"Xia, Y., Qin, T., Ma, W., Yu, N., & Liu, T. -Y. (2016b). Budgeted multi-armed bandits with multiple plays. In IJCAI (pp. 2210\u20132216)."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-019-05799-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-019-05799-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-019-05799-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T04:11:49Z","timestamp":1721275909000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-019-05799-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,16]]},"references-count":37,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["5799"],"URL":"https:\/\/doi.org\/10.1007\/s10994-019-05799-x","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2019,5,16]]},"assertion":[{"value":"23 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}