{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:25:26Z","timestamp":1742912726384,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030242954"},{"type":"electronic","value":"9783030242961"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-24296-1_26","type":"book-chapter","created":{"date-parts":[[2019,6,28]],"date-time":"2019-06-28T21:06:36Z","timestamp":1561755996000},"page":"311-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation"],"prefix":"10.1007","author":[{"given":"Nikki Lijing","family":"Kuang","sequence":"first","affiliation":[]},{"given":"Clement H. C.","family":"Leung","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,29]]},"reference":[{"key":"26_CR1","unstructured":"Ziebart, B.D., Maas, A.L., A. Bagnell, J., Dey, A.K.: Maximum entropy inverse reinforcement learning. In Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI 08), vol. 8, pp. 1433\u20131438 (2008)"},{"key":"26_CR2","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intell. Res."},{"key":"26_CR3","unstructured":"Kearns, M., Singh, S.: Near-optimal reinforcement learning in polynomial time. In: International Conference on Machine Learning (1998)"},{"key":"26_CR4","unstructured":"Santana, H., Ramalho, G., Corruble, V., Ratitch, B.: Multi-agent patrolling with reinforcement learning. In: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, vol. 3, pp. 1122\u20131129. IEEE Computer Society (2004)"},{"key":"26_CR5","first-page":"213","volume":"3","author":"RI Brafman","year":"2002","unstructured":"Brafman, R.I., Tennenholtz, M.: R-max-a general polynomial time algorithm for near-optimal reinforcement learning. J. Mach. Learn. Res. 3, 213\u2013231 (2002)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"26_CR6","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agents Multi-Agent Syst. 11(3), 387\u2013434 (2005)","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Ipek, E., Mutlu, O., Mart\u00ednez, J.F., Caruana, R.: Self-optimizing memory controllers: a reinforcement learning approach. In: ACM SIGARCH Computer Architecture News, vol. 36, no. 3. IEEE Computer Society (2008)","DOI":"10.1145\/1394608.1382172"},{"issue":"22","key":"26_CR8","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 38(22), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C Appl. Rev."},{"key":"26_CR9","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"SV Albrecht","year":"2018","unstructured":"Albrecht, S.V., Stone, P.: Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif. Intell. 258, 66\u201395 (2018)","journal-title":"Artif. Intell."},{"issue":"4","key":"26_CR10","doi-asserted-by":"publisher","first-page":"e0172395","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4), e0172395 (2017)","journal-title":"PLoS ONE"},{"issue":"1","key":"26_CR11","first-page":"103","volume":"13","author":"AW Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: Reinforcement learning with less data and less time. Mach. Learn. 13(1), 103\u2013130 (1993)","journal-title":"Mach. Learn."},{"key":"26_CR12","unstructured":"Brochu, E., Cora, V.M., De Freitas, N.: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint \n                      arXiv:1012.2599\n                      \n                     (2010)"},{"issue":"5","key":"26_CR13","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCYB.2016.2542923","volume":"47","author":"Q Wei","year":"2017","unstructured":"Wei, Q., Lewis, F.L., Sun, Q., Yan, P., Song, R.: Discrete-time deterministic Q-learning: a novel convergence analysis. IEEE Trans. Cybern. 47(5), 1224\u20131237 (2017)","journal-title":"IEEE Trans. Cybern."},{"issue":"3\u20134","key":"26_CR14","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Wiering, M.A.: Using continuous action spaces to solve discrete problems. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN 09), pp. 1149\u20131156. IEEE (2009)","DOI":"10.1109\/IJCNN.2009.5178745"},{"issue":"1","key":"26_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/106365603321828970","volume":"11","author":"N Hansen","year":"2003","unstructured":"Hansen, N., M\u00fcller, S.D., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evol. Comput. 11(1), 1\u201318 (2003)","journal-title":"Evol. Comput."},{"key":"26_CR17","volume-title":"An Introduction to Probability Theory and its Applications","author":"W Feller","year":"2008","unstructured":"Feller, W.: An Introduction to Probability Theory and its Applications, vol. 1, 3rd edn. Wiley, Hoboken (2008)","edition":"3"},{"key":"26_CR18","unstructured":"Rodrigues, C., Cusick, S: Commercial\u00a0Aviation Safety, 5th edn. (2012)"},{"issue":"2","key":"26_CR19","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/TAFFC.2015.2404352","volume":"6","author":"J Deng","year":"2015","unstructured":"Deng, J., Leung, C.H.C.: Dynamic time warping for music retrieval using time series modeling of musical emotions. IEEE Trans. Affect. Comput. 6(2), 137\u2013151 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"26_CR20","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.jcss.2007.04.006","volume":"74","author":"HL Zhang","year":"2008","unstructured":"Zhang, H.L., Leung, C.H.C., Raikundalia, G.K.: Topological analysis of AOCD-based agent networks and experimental results. J. Comput. Syst. Sci. 74, 255\u2013278 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"26_CR21","unstructured":"Azzam, I., Leung, C.H.C., Horwood, J.: Implicit concept-based image indexing and retrieval. In: Proceedings of the IEEE International Conference on Multi-media Modeling, Brisbane, Australia, pp. 354\u2013359 (2004)"},{"key":"26_CR22","series-title":"IFIP International Federation for Information Processing","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-0-387-44641-7_3","volume-title":"Intelligent Information Processing III","author":"HL Zhang","year":"2006","unstructured":"Zhang, H.L., Leung, C.H.C., Raikundalia, G.K.: Classification of intelligent agent network topologies and a new topological description language for agent networks. In: Shi, Z., Shimohara, K., Feng, D. (eds.) IIP 2006. IIFIP, vol. 228, pp. 21\u201331. Springer, Boston, MA (2006). \n                      https:\/\/doi.org\/10.1007\/978-0-387-44641-7_3"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Kuang, N.L.J., Leung, C.H.C., Sung, V.: Stochastic reinforcement learning. In: Proceedings of the IEEE International Conference on Artificial Intelligence and Knowledge Engineering, California, USA, pp. 244\u2013248 (2018)","DOI":"10.1109\/AIKE.2018.00055"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Kuang, N.L.J., Leung, C.H.C.: Performance dynamics and termination errors in reinforcement learning \u2013 a unifying perspective. In: Proceedings of the IEEE International Conference on Artificial Intelligence and Knowledge Engineering, California, USA, pp. 129\u2013133 (2018)","DOI":"10.1109\/AIKE.2018.00028"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2019"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-24296-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,28]],"date-time":"2019-06-28T22:18:41Z","timestamp":1561760321000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-24296-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030242954","9783030242961"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-24296-1_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"29 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Saint Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}