{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:11:47Z","timestamp":1742911907929,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030228071"},{"type":"electronic","value":"9783030228088"}],"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\/978-3-030-22808-8_4","type":"book-chapter","created":{"date-parts":[[2019,6,26]],"date-time":"2019-06-26T00:02:30Z","timestamp":1561507350000},"page":"35-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Regularization in DQN for Parameter-Varying Control Learning Tasks"],"prefix":"10.1007","author":[{"given":"Dazi","family":"Li","sequence":"first","affiliation":[]},{"given":"Chengjia","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Qibing","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Min","family":"Han","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,26]]},"reference":[{"issue":"11","key":"4_CR1","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"4_CR2","unstructured":"Hardt, M., Recht, B., Singer, Y.: Train faster, generalize better: stability of stochastic gradient descent. In: 33rd International Conference on Machine Learning, pp. 1868\u20131877. IMLS Press, New York (2016)"},{"issue":"1","key":"4_CR3","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","volume":"7","author":"CM Bishop","year":"1995","unstructured":"Bishop, C.M.: Training with noise is equivalent to Tikhonov regularization. Neural Comput. 7(1), 108\u2013116 (1995)","journal-title":"Neural Comput."},{"key":"4_CR4","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/978-3-319-12637-1_67","volume-title":"ICONIP 2014","author":"B Chandra","year":"2014","unstructured":"Chandra, B., Sharma, R.K.: Adaptive noise schedule for denoising autoencoder. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds.) ICONIP 2014. LNCS, vol. 8834, pp. 535\u2013542. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-12637-1_67"},{"key":"4_CR5","doi-asserted-by":"crossref","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, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"4_CR6","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT, Cambridge (1998)"},{"key":"4_CR7","unstructured":"Farahmand, A.M., Ghavamzadeh, M., Szepesvari, C., Mannor, S.: Regularized policy iteration. In: 22nd Annual Conference on Neural Information Processing Systems, pp. 441\u2013448. Curran Associates Press, Vancouver (2009)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. arXiv preprint arXiv:1709.06560 (2017)","DOI":"10.1609\/aaai.v32i1.11694"},{"issue":"1","key":"4_CR9","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. JMLR 15(1), 1929\u20131958 (2014)","journal-title":"JMLR"},{"key":"4_CR10","first-page":"2413","volume":"10","author":"AL Strehl","year":"2009","unstructured":"Strehl, A.L., Li, L., Littman, M.L.: Reinforcement learning in finite MDPs: PAC analysis. JMLR 10, 2413\u20132444 (2009)","journal-title":"JMLR"},{"key":"4_CR11","unstructured":"Smith, S.L., Le, Q.V.: Understanding generalization and stochastic gradient descent. arXiv preprint arXiv:1710.06451v1 (2017)"},{"key":"4_CR12","doi-asserted-by":"crossref","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, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Whiteson, S., Tanner, B., Taylor, M.E., Stone, P.: Protecting against evaluation overfitting in empirical reinforcement learning. In: 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, Paris, pp. 120\u2013127. IEEE Press (2011)","DOI":"10.1109\/ADPRL.2011.5967363"},{"key":"4_CR14","unstructured":"Bouthillier, X., Konda, K., Vincent, P., Memisevic, R.: Dropout as data augmentation. arXiv preprint arXiv:1506.08700 (2016)"},{"key":"4_CR15","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. arXiv preprint arXiv:1506.02142 (2015)"},{"key":"4_CR16","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/11564096_32","volume-title":"ECML 2005","author":"M Riedmiller","year":"2005","unstructured":"Riedmiller, M.: Neural fitted Q iteration \u2013 first experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, P.B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS, vol. 3720, pp. 317\u2013328. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11564096_32"},{"key":"4_CR17","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Zaremba, W.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"4_CR18","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1038\/35016072","volume":"405","author":"RHR Hahnloser","year":"2000","unstructured":"Hahnloser, R.H.R., Sarpeshkar, R., Mahowald, M.A., Douglas, R.J., Seung, H.S.: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405, 947\u2013951 (2000)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2019"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-22808-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T16:11:35Z","timestamp":1710259895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-22808-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030228071","9783030228088"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-22808-8_4","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":"26 June 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISNN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Moscow","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":"10 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isnn2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/isnn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}