{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:05:30Z","timestamp":1761401130427,"version":"3.41.2"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2002,11,1]],"date-time":"2002-11-01T00:00:00Z","timestamp":1036108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,11,1]],"date-time":"2002-11-01T00:00:00Z","timestamp":1036108800000},"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":["Machine Learning"],"published-print":{"date-parts":[[2002,11]]},"DOI":"10.1023\/a:1017924227920","type":"journal-article","created":{"date-parts":[[2002,12,30]],"date-time":"2002-12-30T09:36:44Z","timestamp":1041241004000},"page":"111-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Reinforcement Learning for Call Admission Control and Routing under Quality of Service Constraints in Multimedia Networks"],"prefix":"10.1007","volume":"49","author":[{"given":"Hui","family":"Tong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Timothy X","family":"Brown","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"395104_CR1","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/9.75103","volume":"36","author":"E. Altman","year":"1991","unstructured":"Altman, E., & Shwartz, A. (1991). Adaptive control of constrained Markov chains. IEEE Trans. on Auto. Control, 36:4, 454\u2013462.","journal-title":"IEEE Trans. on Auto. Control"},{"key":"395104_CR2","volume-title":"Data networks","author":"D. P. Bertsekas","year":"1992","unstructured":"Bertsekas, D. P., & Gallager, R. (1992). Data networks, 2nd ed. Englewood Cliff, NJ: Prentice Hall.","edition":"2nd ed."},{"key":"395104_CR3","volume-title":"Neural-dynamic programming","author":"D. P. Bertsekas","year":"1996","unstructured":"Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neural-dynamic programming. Belmont, MA: Athena Scientific."},{"key":"395104_CR4","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/0022-247X(85)90288-4","volume":"112","author":"F. J. Beutler","year":"1985","unstructured":"Beutler, F. J., & Ross, K. W. (1985). Optimal policies for controlled Markov chains with a constraint. J. Math. Anal. Appl., 112, 236\u2013252.","journal-title":"J. Math. Anal. Appl."},{"key":"395104_CR5","doi-asserted-by":"crossref","first-page":"341","DOI":"10.2307\/1427303","volume":"18","author":"F. J. Beutler","year":"1986","unstructured":"Beutler, F. J., & Ross, K. W. (1986). Time-average optimal constrained semi-Markov decision processes. Adv. Appl. Prob., 18, 341\u2013359.","journal-title":"Adv. Appl. Prob."},{"key":"395104_CR6","first-page":"671","volume-title":"Advances in NIPS 6","author":"J. A. Boyan","year":"1994","unstructured":"Boyan, J. A., & Littman, M. L. (1994). Packet routing in dynamically changing networks: A reinforcement learning approach. In J. D. Cowan, et al. (Eds.), Advances in NIPS 6 (pp. 671\u2013678). San Francisco: Morgan Kauffman."},{"key":"395104_CR7","series-title":"Performance evaluation and application of ATM networks","first-page":"51","volume-title":"Fifth IFIP Workshop on Performance Modeling & Evaluation of ATM Networks, Ilkley, U.K.","author":"T. X. Brown","year":"1997","unstructured":"Brown, T. X. (1997). Adaptive statistical multiplexing for broadband communications. In Fifth IFIP Workshop on Performance Modeling & Evaluation of ATM Networks, Ilkley, U.K., invited tutorial; also published in D. Kouvatsos (Ed.), Performance evaluation and application of ATM networks (pp. 51\u201379). Boston, MA: Kluwer."},{"key":"395104_CR8","doi-asserted-by":"crossref","unstructured":"Brown, T. X. (2001). Statistical classification based admission control. In R. D. van der Mei et al. (Eds.), Proc. SPIE Conf. on Internet Performance and Control of Network Systems II (Vol. 4523, pp. 1-14).","DOI":"10.1117\/12.434304"},{"key":"395104_CR9","first-page":"982","volume-title":"Advances in neural information processing systems 11","author":"T. X. Brown","year":"1999","unstructured":"Brown, T. X., Tong, H., & Singh, S. (1999). Optimizing admission control while ensuring quality of service in multimedia networks via reinforcement learning. In M. Kearns et al. (Eds.), Advances in neural information processing systems 11 (pp. 982\u2013988). Cambridge, MA: MIT Press."},{"key":"395104_CR10","unstructured":"Carlstrom, J., & Nordstrom, E. (1997). Control of self-similar ATM call traffic by reinforcement learning. In J. Alspector et al. (Eds.), Applications of neural networks to telecommunications 3. LEA Publishers."},{"issue":"4","key":"395104_CR11","doi-asserted-by":"crossref","first-page":"2011","DOI":"10.1109\/TCOMM.1994.583415","volume":"42","author":"Z. Dziong","year":"1994","unstructured":"Dziong, Z., & Mason, L. G. (1994). Call admission and routing in multi-service loss networks. IEEE Trans. Commun., 42:4, 2011\u20132022.","journal-title":"IEEE Trans. Commun."},{"key":"395104_CR12","volume-title":"ATM network resource management","author":"Z. Dziong","year":"1997","unstructured":"Dziong, Z. (1997). ATM network resource management. New York: McGraw-Hill."},{"key":"395104_CR13","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/BF01435458","volume":"39","author":"E. A. Feinberg","year":"1994","unstructured":"Feinberg, E. A. (1994). Constrained semi-Markov decision processes with average reward. ZOR-Math. Methods Oper. Res., 39, 257\u2013288.","journal-title":"ZOR-Math. Methods Oper. Res."},{"key":"395104_CR14","unstructured":"Gabor, Z., Kalmar, Z., & Szepesvari, C. (1998). Multi-criteria reinforcement learning. In Proc. International Conference on Machine Learning, Madison, WI."},{"key":"395104_CR15","doi-asserted-by":"crossref","unstructured":"Krishnan, K. R. (1990). Markov decision algorithms for dynamic routing. IEEE Commun. Mag., Oct., 66-69.","DOI":"10.1109\/35.60368"},{"key":"395104_CR16","doi-asserted-by":"crossref","unstructured":"Lee, W. C., Hluchyj, M. G., & Humblet, P. A. (1995). Routing subject to quality of service constraints in integrated communication networks. IEEE Network, July\/August, 46-55.","DOI":"10.1109\/65.397043"},{"key":"395104_CR17","doi-asserted-by":"crossref","unstructured":"Leland,W. E., Taqqu, M. S., Willingger, W., & Wilson, D. V. (1993). On the self-similar nature of Ethernet traffic. In Proc. of ACM SIGCOMM (pp. 183-193).","DOI":"10.1145\/166237.166255"},{"key":"395104_CR18","doi-asserted-by":"crossref","unstructured":"Marbach, P., & Tsitsiklis, J. N. (1997). A neuro-dynamic approach to admission control in ATM networks: The single link case. In ICASSP.","DOI":"10.1109\/ICASSP.1997.599583"},{"issue":"2","key":"395104_CR19","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/49.824797","volume":"18","author":"P. Marbach","year":"2000","unstructured":"Marbach, P., Mihatsch, O., & Tsitsiklis, J. N. (2000). Call admission control and routing in integrated services networks using neuro-dynamic programming. IEEE J. Sel. Areas Commun., 18:2, 197\u2013208.","journal-title":"IEEE J. Sel. Areas Commun."},{"issue":"5","key":"395104_CR20","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1109\/49.700906","volume":"16","author":"D. Mitra","year":"1998","unstructured":"Mitra, D., Reiman, M. I., & Wang, J. (1998). Robust dynamic admission control for unified cell and call QoS in statistical multiplexers. IEEE J. Sel. Areas Commun., 16:5, 692\u2013707.","journal-title":"IEEE J. Sel. Areas Commun."},{"issue":"5","key":"395104_CR21","doi-asserted-by":"crossref","first-page":"1676","DOI":"10.1109\/25.790549","volume":"48","author":"J. Nie","year":"1999","unstructured":"Nie, J., & Haykin, S. (1999). A Q-learning based dynamic channel assignment technique for mobile communication systems. IEEE Trans. on Vehicular Technology, 48:5, 1676\u20131687.","journal-title":"IEEE Trans. on Vehicular Technology"},{"key":"395104_CR22","doi-asserted-by":"crossref","unstructured":"Pornavalai, C., Chakraborty, G., & Shiratori, N. (1997). Qos based routing algorithm in integrated services packet networks. In Proc. 5th Intl. Conf. on Network Protocols, Atlanta, GA (pp. 167-174).","DOI":"10.1109\/ICNP.1997.643711"},{"key":"395104_CR23","first-page":"974","volume-title":"Advances in NIPS 9","author":"S. P. Singh","year":"1997","unstructured":"Singh, S. P., & Bertsekas, D. P. (1997). Reinforcement learning for dynamic channel allocation in cellular telephone systems. In M. Mozer et al. (Eds.), Advances in NIPS 9 (pp. 974\u2013980). Cambridge, MA: MIT Press."},{"key":"395104_CR24","volume-title":"Reinforcement learning, An introduction","author":"R. S. Sutton","year":"1998","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning, An introduction. Cambridge MA: The MIT Press."},{"key":"395104_CR25","first-page":"1064","volume-title":"Advances in NIPS 10","author":"C. Szepesvari","year":"1998","unstructured":"Szepesvari, Cs. (1998). The asymptotic convergence-rate of Q-learning. In M. Jordan et al. (Eds.), Advances in NIPS 10 (pp. 1064\u20131070). Cambridge, MA: MIT Press."},{"key":"395104_CR26","volume-title":"Adaptive admission control and routing under quality of service constraints in broadband communications","author":"H. Tong","year":"1999","unstructured":"Tong, H. (1999). Adaptive admission control and routing under quality of service constraints in broadband communications. Ph.D. thesis, Dept. of Electrical and Computer Engineering, Univ. of Colorado, Boulder, CO."},{"key":"395104_CR27","unstructured":"Tong, H., & Brown, T. X. (1998). Estimating loss rates in an integrated services network by neural networks. In Proc. IEEE Globecom98, Sydney, Australia."},{"issue":"2","key":"395104_CR28","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1109\/49.824799","volume":"18","author":"H. Tong","year":"2000","unstructured":"Tong, H., & Brown, T. X. (2000). Adaptive call admission control under quality of service constraints: A reinforcement learning solution. IEEE J. Sel. Areas Commun., 18:2, 209\u2013221.","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"395104_CR29","first-page":"279","volume":"8","author":"C. J. C. H. Watkins","year":"1992","unstructured":"Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1017924227920.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1017924227920\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1017924227920.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:37:30Z","timestamp":1752147450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1017924227920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,11]]},"references-count":29,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2002,11]]}},"alternative-id":["395104"],"URL":"https:\/\/doi.org\/10.1023\/a:1017924227920","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2002,11]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}