{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:13:08Z","timestamp":1775189588133,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319925363","type":"print"},{"value":"9783319925370","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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\/978-3-319-92537-0_25","type":"book-chapter","created":{"date-parts":[[2018,5,25]],"date-time":"2018-05-25T07:25:50Z","timestamp":1527233150000},"page":"208-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance Enhancement of Deep Reinforcement Learning Networks Using Feature Extraction"],"prefix":"10.1007","author":[{"given":"Joaquin","family":"Ollero","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Child","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,26]]},"reference":[{"issue":"5786","key":"25_CR1","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"key":"25_CR2","first-page":"679","volume":"6","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech. 6, 679\u2013684 (1957)","journal-title":"J. Math. Mech."},{"issue":"7540","key":"25_CR3","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"25_CR4","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2012","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2012)","journal-title":"J. Artif. Intell. Res."},{"key":"25_CR5","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: AAAI, pp. 2094\u20132100 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"25_CR7","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"25_CR8","unstructured":"Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., de Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2015)"},{"key":"25_CR9","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T.P., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (2016)"},{"issue":"2","key":"25_CR10","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1994","unstructured":"Tesauro, G.: TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6(2), 215\u2013219 (1994)","journal-title":"Neural Comput."},{"issue":"7587","key":"25_CR11","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"7676","key":"25_CR12","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., Hubert, T., Baker, L., Lai, M., Bolton, A., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"key":"25_CR13","unstructured":"Heess, N., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., Eslami, A., Riedmiller, M., et al.: Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:1707.02286 (2017)"},{"key":"25_CR14","unstructured":"Vinyals, O., Ewalds, T., Bartunov, S., Georgiev, P., Vezhnevets, A.S., Yeo, M., Makhzani, A., K\u00fcttler, H., Agapiou, J., Schrittwieser, J., et al.: Starcraft II: a new challenge for reinforcement learning. arXiv preprint arXiv:1708.04782 (2017)"},{"key":"25_CR15","unstructured":"Weber, T., Racani\u00e8re, S., Reichert, D.P., Buesing, L., Guez, A., Rezende, D.J., Badia, A.P., Vinyals, O., Heess, N., Li, Y., et al.: Imagination-augmented agents for deep reinforcement learning. arXiv preprint arXiv:1707.06203 (2017)"},{"key":"25_CR16","unstructured":"Mordvintsev, A., Olah, C., Tyka, M.: Inceptionism: going deeper into neural networks. Google Research Blog, p. 14, Retrieved 20 June 2015"},{"key":"25_CR17","unstructured":"Mordvintsev, A., Olah, C., Tyka, M.: DeepDream - a code example for visualizing neural networks. Google Research (2015)"},{"key":"25_CR18","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"issue":"3\u20134","key":"25_CR19","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":"25_CR20","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of 13th International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2018"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92537-0_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T04:37:27Z","timestamp":1661315847000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92537-0_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319925363","9783319925370"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92537-0_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}