{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:07:12Z","timestamp":1702166832402},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,3,18]],"date-time":"2023-03-18T00:00:00Z","timestamp":1679097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,18]],"date-time":"2023-03-18T00:00:00Z","timestamp":1679097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Swarm Intell"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s11721-023-00224-5","type":"journal-article","created":{"date-parts":[[2023,3,18]],"date-time":"2023-03-18T10:02:37Z","timestamp":1679133757000},"page":"219-251","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent bandit with agent-dependent expected rewards"],"prefix":"10.1007","volume":"17","author":[{"given":"Fan","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,18]]},"reference":[{"key":"224_CR1","unstructured":"Abernethy, J., Lee, C., Sinha, A. & Tewari, A. (2014). Online linear optimization via smoothing. Conference on learning theory, Vol. 35 (pp. 807\u2013823)."},{"key":"224_CR2","unstructured":"Agrawal, S., & Goyal, N. (2013). Further optimal regret bounds for thompson sampling. Artificial intelligence and statistics, Vol. 31 (pp. 99\u2013107)."},{"issue":"4","key":"224_CR3","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/JSAC.2011.110406","volume":"29","author":"A Anandkumar","year":"2011","unstructured":"Anandkumar, A., Michael, N., Tang, A. K., & Swami, A. (2011). Distributed algorithms for learning and cognitive medium access with logarithmic regret. IEEE Journal on Selected Areas in Communications., 29(4), 731\u2013745.","journal-title":"IEEE Journal on Selected Areas in Communications."},{"key":"224_CR4","unstructured":"Bistritz, I., & Leshem, A. (2018). Distributed multi-player bandits-a game of thrones approach. Advances in Neural Information Processing Systems, 31 (pp. 7222\u2013723)."},{"key":"224_CR5","unstructured":"Boucheron, S., Lugosi, G., & Massart, P. (2016). Concentration inequalities: A nonasymptotic theory of independence. Oxford University Press."},{"key":"224_CR6","doi-asserted-by":"crossref","unstructured":"Buccapatnam, S., Eryilmaz, A., & Shroff, N. B. (2013). Multi-armed bandits in the presence of side observations in social networks. In: 52nd IEEE conference on decision and control (pp. 7309\u20137314).","DOI":"10.1109\/CDC.2013.6761049"},{"key":"224_CR7","unstructured":"Cesa-Bianchi, N., Gentile, C., Lugosi, G., & Neu, G. (2017). Boltzmann exploration done right. In: Proceedings of the 31st international conference on neural information processing systems, Vol. 30 (pp. 6287\u20136296)."},{"issue":"1","key":"224_CR8","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1145\/2796314.2745852","volume":"43","author":"R Combes","year":"2015","unstructured":"Combes, R., Magureanu, S., Proutiere, A., & Laroche, C. (2015). Learning to rank: Regret lower bounds and efficient algorithms. SIGMETRICS Performance Evaluation Review, 43(1), 231\u2013244.","journal-title":"SIGMETRICS Performance Evaluation Review"},{"issue":"10","key":"224_CR9","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1016\/j.tree.2015.07.005","volume":"30","author":"DR Farine","year":"2015","unstructured":"Farine, D. R., Montiglio, P.-O., & Spiegel, O. (2015). From individuals to groups and back: The evolutionary implications of group phenotypic composition. Trends in Ecology & Evolution, 30(10), 609\u2013621.","journal-title":"Trends in Ecology & Evolution"},{"issue":"13","key":"224_CR10","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1016\/j.cub.2012.04.050","volume":"22","author":"NO Handegard","year":"2012","unstructured":"Handegard, N. O., Boswell, K. M., Ioannou, C. C., Leblanc, S. P., Tj\u00f8stheim, D. B., & Couzin, I. D. (2012). The dynamics of coordinated group hunting and collective information transfer among schooling prey. Current Biology, 22(13), 1213\u20131217.","journal-title":"Current Biology"},{"key":"224_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, F., Cheng, H., & Chen, G. (2021). Collective decision-making for dynamic environments with visual occlusions. Swarm Intelligence, 16, 7\u201327. https:\/\/link.springer.com\/article\/10.1007\/s11721-021-00200-x","DOI":"10.1007\/s11721-021-00200-x"},{"issue":"4","key":"224_CR12","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1016\/j.anbehav.2013.01.015","volume":"85","author":"JW Jolles","year":"2013","unstructured":"Jolles, J. W., King, A. J., Manica, A., & Thornton, A. (2013). Heterogeneous structure in mixed-species corvid flocks in flight. Animal Behaviour, 85(4), 743\u2013750.","journal-title":"Animal Behaviour"},{"issue":"2","key":"224_CR13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1287\/moor.12.2.262","volume":"12","author":"MN Katehakis","year":"1987","unstructured":"Katehakis, M. N., & Veinott, A. F., Jr. (1987). The multi-armed bandit problem: Decomposition and computation. Mathematics of Operations Research, 12(2), 262\u2013268.","journal-title":"Mathematics of Operations Research"},{"key":"224_CR14","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198508175.001.0001","volume-title":"Living in groups","author":"J Krause","year":"2002","unstructured":"Krause, J., & Ruxton, G. D. (2002). Living in groups. Oxford University Press."},{"key":"224_CR15","doi-asserted-by":"crossref","unstructured":"Landgren, P., Srivastava, V., & Leonard, N. E. (2016a). Distributed cooperative decision-making in multiarmed bandits: Frequentist and bayesian algorithms. In: 2016 IEEE 55th conference on decision and control (CDC) (pp. 167\u2013172).","DOI":"10.1109\/CDC.2016.7798264"},{"key":"224_CR16","doi-asserted-by":"crossref","unstructured":"Landgren, P., Srivastava, V., & Leonard, N. E. (2016b). On distributed cooperative decision-making in multiarmed bandits. In: 2016 European control conference (ECC) (pp. 243\u2013248).","DOI":"10.1109\/ECC.2016.7810293"},{"key":"224_CR17","doi-asserted-by":"crossref","unstructured":"Landgren, P., Srivastava, V., & Leonard, N. E. (2018). Social imitation in cooperative multiarmed bandits: partition-based algorithms with strictly local information. In: 2018 IEEE conference on decision and control (CDC) (pp. 5239\u20135244).","DOI":"10.1109\/CDC.2018.8619744"},{"key":"224_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2020.109445","volume":"125","author":"P Landgren","year":"2021","unstructured":"Landgren, P., Srivastava, V., & Leonard, N. E. (2021). Distributed cooperative decision making in multi-agent multi-armed bandits. Automatica., 125, 109445.","journal-title":"Automatica."},{"key":"224_CR19","unstructured":"Madhushani, U., Dubey, A., Leonard, N., & Pentland, A. (2021). One more step towards reality: Cooperative bandits with imperfect communication. Advances in Neural Information Processing Systems 34, 7813\u20137824."},{"issue":"44","key":"224_CR20","doi-asserted-by":"publisher","first-page":"E10387","DOI":"10.1073\/pnas.1811964115","volume":"115","author":"RP Mann","year":"2018","unstructured":"Mann, R. P. (2018). Collective decision making by rational individuals. Proceedings of the National Academy of Sciences., 115(44), E10387\u2013E10396.","journal-title":"Proceedings of the National Academy of Sciences."},{"issue":"19","key":"224_CR21","doi-asserted-by":"publisher","first-page":"10388","DOI":"10.1073\/pnas.2000840117","volume":"117","author":"RP Mann","year":"2020","unstructured":"Mann, R. P. (2020). Collective decision-making by rational agents with differing preferences. Proceedings of the National Academy of Sciences., 117(19), 10388\u201310396.","journal-title":"Proceedings of the National Academy of Sciences."},{"key":"224_CR22","unstructured":"Mart\u00ednez-Rubio, D., Kanade, V., & Rebeschini, P. (2019). Decentralized cooperative stochastic bandits. In: Proceedings of the 33rd international conference on neural information processing systems, Vol. 32 (pp. 4529\u20134540)."},{"issue":"4","key":"224_CR23","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0003-3472(84)80232-8","volume":"32","author":"M Milinski","year":"1984","unstructured":"Milinski, M. (1984). A predator\u2019s costs of overcoming the confusion-effect of swarming prey. Animal Behaviour., 32(4), 1157\u20131162.","journal-title":"Animal Behaviour."},{"issue":"13","key":"224_CR24","doi-asserted-by":"publisher","first-page":"5263","DOI":"10.1073\/pnas.1217513110","volume":"110","author":"N Miller","year":"2013","unstructured":"Miller, N., Garnier, S., Hartnett, A. T., & Couzin, I. D. (2013). Both information and social cohesion determine collective decisions in animal groups. Proceedings of the National Academy of Sciences, 110(13), 5263\u20135268.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"224_CR25","unstructured":"Perkins, T. J., & Precup, D. (2003). A convergent form of approximate policy iteration. Advances in Neural Information Processing Systems, Vol. 15 (pp. 1627\u20131634)."},{"key":"224_CR26","doi-asserted-by":"crossref","unstructured":"Shahrampour, S., Rakhlin, A., & Jadbabaie, A. (2017). Multi-armed bandits in multi-agent networks. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2786\u20132790).","DOI":"10.1109\/ICASSP.2017.7952664"},{"key":"224_CR27","unstructured":"Shi, C., Shen, C., & Yang, J. (2021). Federated multi-armed bandits with personalization. In: International conference on artificial intelligence and statistics (pp. 2917\u20132925)."},{"key":"224_CR28","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1990). Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. Machine Learning Proceedings (pp. 216\u2013224). Elsevier.","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"224_CR29","unstructured":"Sutton, R. S., McAllester, D. A., Singh, S. P., & Mansour, Y.(2000). Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems, Vol. 12 (pp. 1057\u20131063)."},{"key":"224_CR30","doi-asserted-by":"crossref","unstructured":"Vermorel, J., & Mohri, M. (2005). Multi-armed bandit algorithms and empirical evaluation. In: European conference on machine learning (pp. 437\u2013448).","DOI":"10.1007\/11564096_42"},{"key":"224_CR31","unstructured":"Wang, P.-A., Proutiere, A., Ariu, K., Jedra, Y., & Russo, A. (2020). Optimal algorithms for multiplayer multi-armed bandits. In: Chiappa, S., & Calandra, R. (Eds.), Proceedings of the twenty third international conference on artificial intelligence and statistics (Vol.\u00a0108, pp. 4120\u20134129). PMLR."},{"issue":"19","key":"224_CR32","doi-asserted-by":"publisher","first-page":"6948","DOI":"10.1073\/pnas.0710344105","volume":"105","author":"AJW Ward","year":"2008","unstructured":"Ward, A. J. W., Sumpter, D. J. T., Couzin, I. D., Hart, P. J. B., & Krause, J. (2008). Quorum decision-making facilitates information transfer in fish shoals. Proceedings of the National Academy of Sciences of the United States of America., 105(19), 6948\u20136953.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America."},{"key":"224_CR33","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Zhu, J., Liu, J., & Liu, Y. (2021). Federated bandit: A gossiping approach. In: Abstract proceedings of the 2021 ACM sigmetrics\/international conference on measurement and modeling of computer systems. (pp. 3\u20134).","DOI":"10.1145\/3410220.3453919"}],"container-title":["Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11721-023-00224-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11721-023-00224-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11721-023-00224-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T04:42:59Z","timestamp":1702096979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11721-023-00224-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,18]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["224"],"URL":"https:\/\/doi.org\/10.1007\/s11721-023-00224-5","relation":{},"ISSN":["1935-3812","1935-3820"],"issn-type":[{"value":"1935-3812","type":"print"},{"value":"1935-3820","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,18]]},"assertion":[{"value":"28 May 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"All authors gave their consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}