{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:12:33Z","timestamp":1773058353699,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030014230","type":"print"},{"value":"9783030014247","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\/978-3-030-01424-7_1","type":"book-chapter","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T17:07:37Z","timestamp":1538413657000},"page":"3-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Policy Learning Using SPSA"],"prefix":"10.1007","author":[{"given":"R.","family":"Ramamurthy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Bauckhage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Sifa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Wrobel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,27]]},"reference":[{"key":"1_CR1","volume-title":"Neuro-Dynamic Programming","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas, D.P.: Neuro-Dynamic Programming. Athena Scientific, Belmont (1996)"},{"key":"1_CR2","unstructured":"Brockman, G., et al.: OpenAI Gym. arXiv:1606.01540 (2016)"},{"key":"1_CR3","unstructured":"Chatzidimitriou, K.C., Mitkas, P.A.: A NEAT way for evolving echo state networks. In: Proceedings of European Conference on Artificial Intelligence (2010)"},{"key":"1_CR4","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: Proceedings of International Conference on Machine Learning (2016)"},{"key":"1_CR5","unstructured":"J\u00e4ger, H.: The \u201cecho state\u201d approach to analysing and training recurrent neural networks. Technical report 148, GMD (2001)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Jiang, F., Berry, H., Schoenauer, M.: Supervised and evolutionary learning of echo state networks. In: Proceedings of International Conference on Parallel Problem Solving from Nature (2008)","DOI":"10.1007\/978-3-540-87700-4_22"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Koprinkova-Hristova, P.: Three approaches to train echo state network actors of adaptive critic design. In: Proceeding of International Conference on Artificial Neural Networks (2016)","DOI":"10.1007\/978-3-319-44778-0_58"},{"key":"1_CR8","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Technical reports CMU-CS-93-103, Carnegie-Mellon University (1993)"},{"key":"1_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-642-35289-8_36","volume-title":"Neural Networks: Tricks of the Trade","author":"M Luko\u0161evi\u010dius","year":"2012","unstructured":"Luko\u0161evi\u010dius, M.: A practical guide to applying echo state networks. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 659\u2013686. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_36"},{"key":"1_CR10","unstructured":"Mania, H., Guy, A., Recht, B.: Simple random search provides a competitive approach to reinforcement learning. arXiv:1803.07055 (2018)"},{"key":"1_CR11","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of International Conference on Machine Learning (2016)"},{"issue":"7540","key":"1_CR12","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"issue":"3","key":"1_CR13","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22(3), 400\u2013407 (1951)","journal-title":"Ann. Math. Stat."},{"key":"1_CR14","unstructured":"Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv:1703.03864 (2017)"},{"issue":"3","key":"1_CR15","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1162\/neco.2007.19.3.757","volume":"19","author":"J Schmidhuber","year":"2007","unstructured":"Schmidhuber, J., Wierstra, D., Gagliolo, M., Gomez, F.: Training recurrent networks by Evolino. Neural Comput. 19(3), 757\u2013779 (2007)","journal-title":"Neural Comput."},{"issue":"7\u20139","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1016\/j.neucom.2007.12.020","volume":"71","author":"B Schrauwen","year":"2008","unstructured":"Schrauwen, B., Wardermann, M., Verstraeten, D., Steil, J.J., Stroobandt, D.: Improving reservoirs using intrinsic plasticity. Neurocomputing 71(7\u20139), 1159\u20131171 (2008)","journal-title":"Neurocomputing"},{"issue":"7676","key":"1_CR17","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"issue":"3","key":"1_CR18","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/9.119632","volume":"37","author":"JC Spall","year":"1992","unstructured":"Spall, J.C.: Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Autom. Control. 37(3), 332\u2013341 (1992)","journal-title":"IEEE Trans. Autom. Control."},{"key":"1_CR19","unstructured":"Such, F.P., Madhavan, V., Conti, E., Lehman, J., Stanley, K.O., Clune, J.: Deep neuroevolution: genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv:1712.06567 (2017)"},{"key":"1_CR20","unstructured":"Sutton, R.: Introduction to reinforcement learning with function approximation. In: Tutorial at the Conference on Neural Information Processing Systems (2015)"},{"key":"1_CR21","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G., et al.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01424-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:30:42Z","timestamp":1773048642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01424-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030014230","9783030014247"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01424-7_1","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":"27 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rhodes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"4 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"360","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":"139","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":"28","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":"39% - 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":"2","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":"4","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)"}},{"value":"In addition there are 41 full poster papers and 11 short poster papers included in the proceedings","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}