{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:09:25Z","timestamp":1782965365387,"version":"3.54.5"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030030971","type":"print"},{"value":"9783030030988","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-03098-8_18","type":"book-chapter","created":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T08:27:33Z","timestamp":1540283253000},"page":"296-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["A Deep Reinforcement Learning Approach for Large-Scale Service Composition"],"prefix":"10.1007","author":[{"given":"Ahmed","family":"Moustafa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takayuki","family":"Ito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,24]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Al-Masri, E., Mahmoud, Q.H.: Discovering the best web service. In: Proceedings of WWW, pp. 1257\u20131258 (2007)","DOI":"10.1145\/1242572.1242795"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Lee, C.-H., Hwang, S.-Y., Yen, I.-L.: A service pattern model for flexible service composition. In: Proceedings of IEEE ICWS, pp. 626\u2013627, June 2012","DOI":"10.1109\/ICWS.2012.58"},{"issue":"2","key":"18_CR3","first-page":"140","volume":"4","author":"D Chiu","year":"2012","unstructured":"Chiu, D., Agrawal, G.: Cost and accuracy aware scientific workflow composition for service-oriented environments. IEEE Trans. Serv. Comput. 4(2), 140\u2013152 (2012)","journal-title":"IEEE Trans. Serv. Comput."},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: Proceedings of ICML, ICML 2007, pp. 273\u2013280. ACM, New York (2007)","DOI":"10.1145\/1273496.1273531"},{"issue":"1","key":"18_CR5","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1587\/transcom.E96.B.10","volume":"96\u2013B","author":"J Huang","year":"2013","unstructured":"Huang, J., Liu, Y., Yu, R., Duan, Q., Tanaka, Y.: Modeling and algorithms for QoS-aware service composition in virtualization-based cloud computing. IEICE Trans. 96\u2013B(1), 10\u201319 (2013)","journal-title":"IEICE Trans."},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Jureta, I.J., Faulkner, S., Achbany, Y., Saerens, M.: Dynamic web service composition within a service-oriented architecture. In: IEEE International Conference on Web Services, ICWS 2007, pp. 304\u2013311, July 2007","DOI":"10.1109\/ICWS.2007.79"},{"issue":"3","key":"18_CR7","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/TSC.2013.2","volume":"7","author":"A Klein","year":"2014","unstructured":"Klein, A., Ishikawa, F., Honiden, S.: SanGA: a self-adaptive network-aware approach to service composition. IEEE Trans. Serv. Comput. 7(3), 452\u2013464 (2014)","journal-title":"IEEE Trans. Serv. Comput."},{"key":"18_CR8","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS, NIPS 2012, pp. 1097\u20131105. Curran Associates Inc. (2012)"},{"issue":"1","key":"18_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/72.554195","volume":"8","author":"S Lawrence","year":"1997","unstructured":"Lawrence, S., Giles, C.L., Tsoi, A.C., Back, A.D.: Face recognition: a convolutional neural-network approach. IEEE Trans. Neural Netw. 8(1), 98\u2013113 (1997)","journal-title":"IEEE Trans. Neural Netw."},{"issue":"3","key":"18_CR10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0898-1221(97)00282-4","volume":"35","author":"D Li","year":"1998","unstructured":"Li, D., Cheung, D., Shi, X., Ng, V.: Uncertainty reasoning based on cloud models in controllers. Comput. Math. Appl. 35(3), 99\u2013123 (1998)","journal-title":"Comput. Math. Appl."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Li, H., Dagli, C.H., Enke, D.: Short-term stock market timing prediction under reinforcement learning schemes. In: Proceedings of IEEE ADPRL, pp. 233\u2013240 (2007)","DOI":"10.1109\/ADPRL.2007.368193"},{"issue":"7540","key":"18_CR12","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"18_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-642-31095-9_31","volume-title":"Advanced Information Systems Engineering","author":"A Moustafa","year":"2012","unstructured":"Moustafa, A., Zhang, M.: Towards proactive web service adaptation. In: Ralyt\u00e9, J., Franch, X., Brinkkemper, S., Wrycza, S. (eds.) CAiSE 2012. LNCS, vol. 7328, pp. 473\u2013485. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31095-9_31"},{"key":"18_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/978-3-642-45005-1_21","volume-title":"Service-Oriented Computing","author":"A Moustafa","year":"2013","unstructured":"Moustafa, A., Zhang, M.: Multi-objective service composition using reinforcement learning. In: Basu, S., Pautasso, C., Zhang, L., Fu, X. (eds.) ICSOC 2013. LNCS, vol. 8274, pp. 298\u2013312. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-45005-1_21"},{"key":"18_CR15","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: Proceedings of ICLR, Puerto Rico (2016)"},{"issue":"7587","key":"18_CR16","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"18_CR17","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1007\/978-94-007-2169-2_170","volume-title":"Green Communications and Networks","author":"H Tang","year":"2012","unstructured":"Tang, H., Liu, W., Zhou, L.: Web service composition method using hierarchical reinforcement learning. In: Yang, Y., Ma, M. (eds.) Green Communications and Networks. LNEE, vol. 113, pp. 1429\u20131438. Springer, Dordrecht (2012). https:\/\/doi.org\/10.1007\/978-94-007-2169-2_170"},{"key":"18_CR18","unstructured":"Van Hasselt, H.: Double q-learning. In: Proceedings of NIPS, pp. 2613\u20132621. Curran Associates Inc. (2010)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of AAAI, AAAI 2016, pp. 2094\u20132100. AAAI Press (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"18_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-662-45391-9_11","volume-title":"Service-Oriented Computing","author":"H Wang","year":"2014","unstructured":"Wang, H., Chen, X., Wu, Q., Yu, Q., Zheng, Z., Bouguettaya, A.: Integrating on-policy reinforcement learning with multi-agent techniques for adaptive service composition. In: Franch, X., Ghose, A.K., Lewis, G.A., Bhiri, S. (eds.) ICSOC 2014. LNCS, vol. 8831, pp. 154\u2013168. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-662-45391-9_11"},{"key":"18_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1007\/978-3-642-37401-2_23","volume-title":"Web Technologies and Applications","author":"H Wang","year":"2013","unstructured":"Wang, H., Wang, X.: A novel approach to large-scale services composition. In: Ishikawa, Y., Li, J., Wang, W., Zhang, R., Zhang, W. (eds.) APWeb 2013. LNCS, vol. 7808, pp. 220\u2013227. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37401-2_23"},{"key":"18_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-642-17358-5_7","volume-title":"Service-Oriented Computing","author":"H Wang","year":"2010","unstructured":"Wang, H., Zhou, X., Zhou, X., Liu, W., Li, W., Bouguettaya, A.: Adaptive service composition based on reinforcement learning. In: Maglio, P.P., Weske, M., Yang, J., Fantinato, M. (eds.) ICSOC 2010. LNCS, vol. 6470, pp. 92\u2013107. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-17358-5_7"},{"issue":"4","key":"18_CR23","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1504\/IJWGS.2011.044696","volume":"7","author":"S Wang","year":"2011","unstructured":"Wang, S., Zheng, Z., Sun, Q., Zou, H., Yang, F.: Reliable web service selection via QoS uncertainty computing. Int. J. Web Grid Serv. 7(4), 410\u2013426 (2011)","journal-title":"Int. J. Web Grid Serv."},{"key":"18_CR24","unstructured":"Watkins, C.: Learning from delayed rewards. Ph.D. thesis, Cambridge University, England (1989)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Wenbo, X., Jian, C., Haiyan, Z., Lei, W.: A multi-agent learning model for service composition. In: Proceedings of APSCC, pp. 70\u201375, December 2012","DOI":"10.1109\/APSCC.2012.44"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Won Lee, J.: Stock price prediction using reinforcement learning. In: Proceedings of IEEE ISIE, vol. 1, pp. 690\u2013695 (2001)","DOI":"10.1109\/ISIE.2001.931880"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-642-20152-3_24","volume-title":"Database Systems for Advanced Applications","author":"Z Ye","year":"2011","unstructured":"Ye, Z., Zhou, X., Bouguettaya, A.: Genetic algorithm based QoS-aware service compositions in cloud computing. In: Yu, J.X., Kim, M.H., Unland, R. (eds.) DASFAA 2011. LNCS, vol. 6588, pp. 321\u2013334. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-20152-3_24"},{"issue":"3","key":"18_CR28","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1109\/TSC.2011.17","volume":"5","author":"D Zuohua","year":"2012","unstructured":"Zuohua, D., Mingyue, J., Kandel, A.: Port-based reliability computing for service composition. IEEE Trans. Serv. Comput. 5(3), 422\u2013436 (2012)","journal-title":"IEEE Trans. Serv. Comput."}],"container-title":["Lecture Notes in Computer Science","PRIMA 2018: Principles and Practice of Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03098-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:15:27Z","timestamp":1775250927000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03098-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030030971","9783030030988"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03098-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"24 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRIMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Principles and Practice of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tokyo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"prima2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2018.prima-conference.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"103","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}