{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T14:36:49Z","timestamp":1648910209782},"reference-count":20,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2014,3,27]],"date-time":"2014-03-27T00:00:00Z","timestamp":1395878400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"DOI":"10.1007\/s11277-014-1684-4","type":"journal-article","created":{"date-parts":[[2014,3,26]],"date-time":"2014-03-26T18:23:37Z","timestamp":1395858217000},"source":"Crossref","is-referenced-by-count":0,"title":["Coping with Network Dynamics Using Reinforcement Learning Based Network Optimization in Wireless Sensor Networks"],"prefix":"10.1007","author":[{"given":"Milos","family":"Rovcanin","sequence":"first","affiliation":[]},{"given":"Eli","family":"De Poorter","sequence":"additional","affiliation":[]},{"given":"Ingrid","family":"Moerman","sequence":"additional","affiliation":[]},{"given":"Piet","family":"Demeester","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,3,27]]},"reference":[{"issue":"6","key":"1684_CR1","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1007\/s11276-011-0356-5","volume":"17","author":"E Poorter De","year":"2011","unstructured":"De Poorter, E., Troubleyn, E., Moerman, I., & Demeester, P. (2011). IDRA: A flexible system architecture for next generation wireless sensor networks. Wireless Networks, 17(6), 1423\u20131440.","journal-title":"Wireless Networks"},{"key":"1684_CR2","unstructured":"Rovcanin, M., De Poorter, E., Moerman, I., & Demeester, P. A reinforcement learning based solution for cognitive network cooperation between co-located, heterogeneous wireless sensor networks. ADHoc Journal."},{"key":"1684_CR3","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C. J. C. H., & Dayan, P. (1992). Technical note Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"},{"key":"1684_CR4","doi-asserted-by":"crossref","unstructured":"Sutton, R. S. (1988). Learning to predict by the methods of temporal differences. Machine Learning, 3(1).","DOI":"10.1007\/BF00115009"},{"key":"1684_CR5","unstructured":"Bertsekas, D. P. (2010). Approximate policy iteration: A survey and some new methods. Journal of Control Theory and Applications, 9, 310\u2013335. Report LIDS-2833."},{"key":"1684_CR6","unstructured":"Perkins, T. J., & Precup, D. (2002). A convergent form of approximate policy iteration. In Advance in neural information processing systems 15, NIPS 2002, 9\u201314 December, 2002, Vancouver, British Columbia, Canada."},{"key":"1684_CR7","unstructured":"Lanza-Gutierrez, J. M., Gomez-Pulido, J. A., Vega-Rodriguez, M. A., & Sanchez-Perez J. M. (2012). Multi-objective evolutionary algorithms for energy-efficiency in heterogeneous wireless sensor networks. In SAS 2012: IEEE sensors applications symposium, 7\u20139 February, 2012, Brescia, Italy."},{"key":"1684_CR8","doi-asserted-by":"crossref","unstructured":"Deb, K., Agrawal, S., Pratap, A., & Meyarivan, T. (2000). A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II. In Parallel problem solving from nature PPSN VI.","DOI":"10.1007\/3-540-45356-3_83"},{"key":"1684_CR9","unstructured":"Zitzler, E., Laumanns, M., & Thiele, L. (2001). SPEA2: Improving the strength Pareto evolutionary algorithm. In EUROGEN 2001."},{"key":"1684_CR10","unstructured":"\u00d6zdemir, S., Baraa, A. A., & Khalil, \u00d6. A. Multi-objective evolutionary algorithm based on decomposition for energy efficient coverage in wireless sensor networks."},{"key":"1684_CR11","volume-title":"Evolutionary algorithms for solving multi-objective problems","author":"CAC Coello","year":"2007","unstructured":"Coello, C. A. C., Lamont, G. B., & Van Veldhuizen, D. A. (2007). Evolutionary algorithms for solving multi-objective problems (2nd ed.). Berlin: Springer.","edition":"2"},{"key":"1684_CR12","doi-asserted-by":"crossref","unstructured":"De Poorter, E., Latre, B., Moerman, I., & Demeester, P. (2008). Symbiotic networks: Towards a new level of cooperation between wireless networks. Special issue of the Wireless Personal Communications Journal, 45(4), 479\u2013495.","DOI":"10.1007\/s11277-008-9490-5"},{"key":"1684_CR13","doi-asserted-by":"crossref","unstructured":"Dietterich, T. G., & Langley, O. (2007). Machine learning for cognitive networks:Technology assessment and research challenges in cognitive networks: Towards self aware networks. Wiley, Chichester. doi: 10.1002\/9780470515143.ch5 .","DOI":"10.1002\/9780470515143.ch5"},{"key":"1684_CR14","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelblign","year":"1996","unstructured":"Kaelblign, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement learning: A survey. Journal of Artificial Intelligence Research, 4, 237\u2013285.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"1684_CR15","first-page":"1107","volume":"4","author":"MG Lagoudakis","year":"2003","unstructured":"Lagoudakis, M. G., & Parr, R. (2003). Least-squares policy iteration. Journal of Machine Learning Research, 4, 1107\u20131149.","journal-title":"Journal of Machine Learning Research"},{"key":"1684_CR16","unstructured":"Lagoudakis, M., & Parr, R. (2001). Model-free least-squares policy iteration. In Proceedings of NIPS."},{"key":"1684_CR17","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Babuska, R., De Schutter, B., & Ernst, D. (2010). Reinforcement learning and dynamic programming using function approximators. Taylor and Francis, London. ISBN:978-1-4398-2108-4 (Hardback).","DOI":"10.1201\/9781439821091"},{"key":"1684_CR18","unstructured":"Tytgat, L., Jooris, B., De Mil, P., Latr, B., Moerman, I., & Demeester, P. (2009). UGentWiLab, a real-life wireless sensor testbed with environment emulation. In 6th European conference on wireless sensor networks (EWSN 2009). https:\/\/biblio.ugent.be\/publication\/676545 ."},{"key":"1684_CR19","doi-asserted-by":"crossref","unstructured":"Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. A Bradford book. MIT Press, Cambridge, MA.","DOI":"10.1109\/TNN.1998.712192"},{"key":"1684_CR20","unstructured":"White, J. M. (2012). Bandit algorithms for website optimization. O\u2019Rilley Media, Sebastopol."}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-014-1684-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11277-014-1684-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-014-1684-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T23:26:06Z","timestamp":1565306766000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11277-014-1684-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3,27]]},"references-count":20,"alternative-id":["1684"],"URL":"https:\/\/doi.org\/10.1007\/s11277-014-1684-4","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3,27]]}}}