{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T20:22:45Z","timestamp":1694636565505},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2009,8,4]],"date-time":"2009-08-04T00:00:00Z","timestamp":1249344000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Telecommun Syst"],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1007\/s11235-009-9184-7","type":"journal-article","created":{"date-parts":[[2009,8,3]],"date-time":"2009-08-03T17:00:46Z","timestamp":1249318846000},"page":"249-261","source":"Crossref","is-referenced-by-count":3,"title":["State-dependent packet scheduling for QoS routing in\u00a0a\u00a0dynamically changing environment"],"prefix":"10.1007","volume":"42","author":[{"given":"Malika","family":"Bourenane","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelhamid","family":"Mellouk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Djilali","family":"Benhamamouch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,8,4]]},"reference":[{"key":"9184_CR1","doi-asserted-by":"crossref","unstructured":"Anker, T., Cohen, R., Dolev, D., & Singer, Y. (2001). Probabilistic fair queuing. In IEEE 2001 workshop on high performance switching and routing (pp. 397\u2013401).","DOI":"10.1109\/HPSR.2001.923668"},{"key":"9184_CR2","doi-asserted-by":"crossref","unstructured":"Baird, K. (1995). Residual algorithms: reinforcement learning with function approximation. In Machine learning twelfth international conference. San Francisco, USA.","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"9184_CR3","volume-title":"Dynamic programming","author":"R. E. Bellman","year":"1957","unstructured":"Bellman, R. E. (1957). Dynamic programming. Princeton: Princeton University Press."},{"key":"9184_CR4","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195131581.001.0001","volume-title":"From natural to artificial swarm intelligence","author":"E. Bonabeau","year":"1999","unstructured":"Bonabeau, E., Dorigo, M., & Theraulaz, G. (1999). From natural to artificial swarm intelligence. London: Oxford University Press."},{"issue":"2","key":"9184_CR5","first-page":"138","volume":"2","author":"M. Bourenane","year":"2007","unstructured":"Bourenane, M., Mellouk, A., & Benhamamouch, D. (2007). A\u00a0QoS-based scheduling by neurodynamic learning. System and Information Sciences Journal, 2(2), 138\u2013144.","journal-title":"System and Information Sciences Journal"},{"key":"9184_CR6","unstructured":"Boutilier, C. (1999). Sequential optimality and coordination in multiagent systems. In IJCAI (pp. 478\u2013485)."},{"key":"9184_CR7","volume-title":"Deploying IP and MPLS QoS for multiservice networks: theory and practice","author":"J. Evans","year":"2007","unstructured":"Evans, J., & Filsfils, C. (2007). Deploying IP and MPLS QoS for multiservice networks: theory and practice. San Mateo: Morgan Kaufmann."},{"key":"9184_CR8","unstructured":"Ferra, H., Lau, K., Leckie, C., & Tang, A. Applying reinforcement learning to packet scheduling in routers. In Proceedings of the fifteenth innovative applications of artificial intelligence conference (IAAI-03) (pp. 79\u201384). 12\u201314 August 2003, Acapulco, Mexico."},{"key":"9184_CR9","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/S0166-3615(03)00123-4","volume":"53","author":"Hadeli","year":"2004","unstructured":"Hadeli, Valckenaers, P., Kollingbaum, M., & Van Brussel, H. (2004). Multi-agent coordination and control using stigmergy. Computers in Industry, 53, 75\u201396.","journal-title":"Computers in Industry"},{"key":"9184_CR10","doi-asserted-by":"crossref","unstructured":"Hall, J., & Mars, P. (1998). Satisfying QoS with a learning based scheduling algorithm. In 6th international workshop on quality of service (pp. 171\u2013176).","DOI":"10.1109\/IWQOS.1998.675236"},{"key":"9184_CR11","first-page":"1039","volume":"4","author":"J. Hu","year":"2003","unstructured":"Hu, J., & Wellman, M. P. (2003). Nash Q-learning for general-sum stochastic games. Journal of Machine Learning Research, 4, 1039\u20131069.","journal-title":"Journal of Machine Learning Research"},{"key":"9184_CR12","first-page":"164","volume-title":"Lecture notes in computer science","author":"S. Hoceini","year":"2005","unstructured":"Hoceini, S., Mellouk, A., & Amirat, Y. (2005). K-shortest paths Q-routing: a new QoS routing algorithm in telecommunication networks. In Lecture notes in computer science (Vol. 3421, pp.\u00a0164\u2013172). Berlin: Springer."},{"key":"9184_CR13","unstructured":"Kapetanakis, S., & Kudenko, D. (2002). Reinforcement learning of coordination in cooperative multi-agent systems. In AAAI 2002 (pp. 326\u2013331)."},{"key":"9184_CR14","unstructured":"Kortebi, A., Muscariello, L., Oueslati, S., & Roberts, J. (2004). On the scalability of fair queuing. In Proc. of ACM hot nets III. San\u00a0Diego."},{"key":"9184_CR15","volume-title":"End-to-end quality of service engineering in next generation heterogeneous networks","author":"A. Mellouk","year":"2008","unstructured":"Mellouk, A. (2008). End-to-end quality of service engineering in next generation heterogeneous networks. New York: Wiley."},{"key":"9184_CR16","first-page":"299","volume-title":"Lecture notes in artificial intelligence","author":"A. Mellouk","year":"2005","unstructured":"Mellouk, A., & Hoceini, S. (2005). A reinforcement learning approach for QoS based routing packets in integrated service web based systems. In Lecture notes in artificial intelligence (Vol.\u00a03528, pp. 299\u2013305). Berlin: Springer."},{"key":"9184_CR17","unstructured":"Mellouk, A., & Chebira, A. (2009). Machine learning. I-TECH Education and Publishing Ed., Intechweb.org."},{"issue":"10","key":"9184_CR18","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1002\/dac.858","volume":"20","author":"A. Mellouk","year":"2007","unstructured":"Mellouk, A., Hoceini, S., & Amirat, Y. (2007). Adaptive quality of service based routing approaches: development of a neuro-dynamic state-dependent reinforcement learning algorithm. International Journal of Communication Systems, 20(10), 1113\u20131130.","journal-title":"International Journal of Communication Systems"},{"issue":"2","key":"9184_CR19","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/MCOM.2007.313396","volume":"45","author":"A. Mellouk","year":"2007","unstructured":"Mellouk, A., Lorenz, P., Boukerche, A., & Lee, M. H. (2007). Impact of adaptive quality of service based routing algorithms in the next generation heterogeneous networks. IEEE Communication Magazine, 45(2), 65\u201366.","journal-title":"IEEE Communication Magazine"},{"issue":"11","key":"9184_CR20","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.1016\/j.comcom.2007.03.010","volume":"31","author":"A. Mellouk","year":"2008","unstructured":"Mellouk, A., Hoceini, S., & Cheurfa, M. (2008). Reinforcing probabilistic selective quality of service routes in dynamic heterogeneous networks. Computer Communication, 31(11), 2706\u20132715.","journal-title":"Computer Communication"},{"issue":"2","key":"9184_CR21","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/j.1468-0394.2004.00265.x","volume":"21","author":"N. Monekosso","year":"2004","unstructured":"Monekosso, N., & Remagnino, P. (2004). The analysis and performance evaluation of the pheromone-Q-learning algorithm. Expert Systems, 21(2), 80\u201391.","journal-title":"Expert Systems"},{"key":"9184_CR22","doi-asserted-by":"crossref","unstructured":"Nichols, K., Blake, S., Baker, F., & Black, D. (1998). Definition of the differentiated services field (DS field) in the IPv4 and IPv6 headers. In RFC 2474.","DOI":"10.17487\/rfc2474"},{"key":"9184_CR23","first-page":"25","volume":"4\/05","author":"S. Nouyan","year":"2005","unstructured":"Nouyan, S., Ghizzioli, R., Birattari, M., & Dorigo, M. (2005). An insect-based algorithm for the dynamic task allocation problem. K\u00fcnstliche Intelligenz, 4\/05, 25\u201331.","journal-title":"K\u00fcnstliche Intelligenz"},{"key":"9184_CR24","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"M. Puterman","year":"2005","unstructured":"Puterman, M. (2005). Markov decision processes: discrete stochastic dynamic programming. New York: Wiley."},{"issue":"3","key":"9184_CR25","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1109\/90.502236","volume":"4","author":"M. Shreedhar","year":"1996","unstructured":"Shreedhar, M., & Varghese, G. (1996). Efficient fair queuing using deficit round robin. IEEE\/ACM Transactions on Networking, 4(3), 375\u2013385.","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"9184_CR26","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: MIT Press."},{"key":"9184_CR27","volume-title":"A concise introduction to multiagent systems and distributed AI","author":"N. Vlassis","year":"2003","unstructured":"Vlassis, N. (2003). A concise introduction to multiagent systems and distributed AI. San Rafael: Morgan & Claypool Publishers. Informatics Institute, University of Amsterdam, pp. 2, 19, 21, 30, 31, 35, 115, 129."},{"key":"9184_CR28","unstructured":"Wang, H., Shen, C., & Shin, K. (2001). Adaptive-weighted packet scheduling for premium service. In IEEE int. conf. on communications (ICC 2001) (pp. 1846\u20131850)."},{"key":"9184_CR29","unstructured":"Watkins, J. C. H. (1989). Learning from delayed rewards. Ph.D. thesis, King\u2019s College of Cambridge, UK."},{"issue":"3","key":"9184_CR30","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(3), 279\u2013292.","journal-title":"Machine Learning"},{"key":"9184_CR31","unstructured":"Weinberg, M., & Rosenschein, J. S. Best-response multiagent learning in nonstationary environments. In Proceedings of the third international joint conference on autonomous agents and multi-agent systems (AAMAS-04). Columbia University, New York City, July 2004."}],"container-title":["Telecommunication Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-009-9184-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11235-009-9184-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11235-009-9184-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,9]],"date-time":"2021-10-09T08:39:00Z","timestamp":1633768740000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11235-009-9184-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,8,4]]},"references-count":31,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2009,12]]}},"alternative-id":["9184"],"URL":"https:\/\/doi.org\/10.1007\/s11235-009-9184-7","relation":{},"ISSN":["1018-4864","1572-9451"],"issn-type":[{"value":"1018-4864","type":"print"},{"value":"1572-9451","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,8,4]]}}}