{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T07:14:58Z","timestamp":1758266098498,"version":"3.40.3"},"publisher-location":"Cham","reference-count":8,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319466866"},{"type":"electronic","value":"9783319466873"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46687-3_2","type":"book-chapter","created":{"date-parts":[[2016,9,28]],"date-time":"2016-09-28T09:13:24Z","timestamp":1475054004000},"page":"13-22","source":"Crossref","is-referenced-by-count":16,"title":["Deep Q-Learning with Prioritized Sampling"],"prefix":"10.1007","author":[{"given":"Jianwei","family":"Zhai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haijun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cijia","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,29]]},"reference":[{"key":"2_CR1","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Playing atari with deep reinforcement learning. In: Deep Learning Workshop of the 27th Advances in Neural Information Processing Systems, NIPS, Lake Tahoe (2013)"},{"issue":"7540","key":"2_CR2","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., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"2_CR3","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., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"2_CR4","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"2_CR5","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Technical report, DTIC Document (1993)"},{"issue":"5","key":"2_CR6","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"JN Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van, R.B.: An analysis of temporal-difference learning with function approximation. IEEE Trans. Autom. Control 42(5), 674\u2013690 (1997)","journal-title":"IEEE Trans. Autom. Control"},{"issue":"4","key":"2_CR7","first-page":"212","volume":"3","author":"GE Hinton","year":"2012","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., et al.: Improving neural networks by preventing co-adaptation of feature detectors. Comput. Sci. 3(4), 212\u2013223 (2012)","journal-title":"Comput. Sci."},{"issue":"1","key":"2_CR8","first-page":"253","volume":"47","author":"MG Bellemare","year":"2012","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., et al.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47(1), 253\u2013279 (2012)","journal-title":"J. Artif. Intell. Res."}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46687-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,4,19]],"date-time":"2017-04-19T10:50:34Z","timestamp":1492599034000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46687-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319466866","9783319466873"],"references-count":8,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46687-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}