{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T01:52:54Z","timestamp":1770515574910,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Singapore","isbn-type":[{"value":"9789811513763","type":"print"},{"value":"9789811513770","type":"electronic"}],"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\/978-981-15-1377-0_58","type":"book-chapter","created":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T07:03:36Z","timestamp":1573628616000},"page":"752-765","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Q-Learning with Phased Experience Cooperation"],"prefix":"10.1007","author":[{"given":"Hongbo","family":"Wang","sequence":"first","affiliation":[]},{"given":"Fanbing","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Xuyan","family":"Tu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,14]]},"reference":[{"issue":"3\u20134","key":"58_CR1","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":"58_CR2","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"58_CR3","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"issue":"4","key":"58_CR4","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1137\/S0363012901385691","volume":"42","author":"VR Konda","year":"2003","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Onactor-critic algorithms. SIAM J. Control Optim. 42(4), 1143\u20131166 (2003)","journal-title":"SIAM J. Control Optim."},{"key":"58_CR5","unstructured":"Bhatnagar, S., Ghavamzadeh, M., Lee, M., Sutton, R.S.: Incremental natural actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 105\u2013112 (2008)"},{"issue":"6","key":"58_CR6","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","volume":"42","author":"I Grondman","year":"2012","unstructured":"Grondman, I., Busoniu, L., Lopes, G.A., Babuska, R.: A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(6), 1291\u20131307 (2012)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.)"},{"key":"58_CR7","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"58_CR8","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms (2014)"},{"key":"58_CR9","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"58_CR10","doi-asserted-by":"crossref","unstructured":"Narasimhan, K., Kulkarni, T., Barzilay, R.: Language understanding for text-based games using deep reinforcement learning. arXiv preprint arXiv:1506.08941 (2015)","DOI":"10.18653\/v1\/D15-1001"},{"key":"58_CR11","unstructured":"Zelinka, M.: Using reinforcement learning to learn how to play text-based games. arXiv preprint arXiv:1801.01999 (2018)"},{"key":"58_CR12","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"58_CR13","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":"58_CR14","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70. pp. 449\u2013458. JMLR.org (2017)"},{"key":"58_CR15","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"issue":"7540","key":"58_CR16","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":"9","key":"58_CR17","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1016\/j.tins.2015.07.004","volume":"38","author":"LA Atherton","year":"2015","unstructured":"Atherton, L.A., Dupret, D., Mellor, J.R.: Memory trace replay: the shaping of memory consolidation by neuromodulation. Trends Neurosci. 38(9), 560\u2013570 (2015)","journal-title":"Trends Neurosci."},{"issue":"12","key":"58_CR18","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1038\/nn.3843","volume":"17","author":"CG McNamara","year":"2014","unstructured":"McNamara, C.G., Tejero-Cantero, \u00c1., Trouche, S., Campo-Urriza, N., Dupret, D.: Dopaminergic neurons promote hippocampal reactivation and spatial memory persistence. Nat. Neurosci. 17(12), 1658 (2014)","journal-title":"Nat. Neurosci."},{"key":"58_CR19","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/S0079-6123(06)65034-6","volume":"165","author":"GE Hinton","year":"2007","unstructured":"Hinton, G.E.: To recognize shapes, first learn to generate images. Progr. Brain Res. 165, 535\u2013547 (2007)","journal-title":"Progr. Brain Res."},{"key":"58_CR20","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"issue":"2","key":"58_CR21","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1109\/TSMCC.2011.2106494","volume":"42","author":"S Adam","year":"2011","unstructured":"Adam, S., Busoniu, L., Babuska, R.: Experience replay for real-time reinforcement learning control. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(2), 201\u2013212 (2011)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.)"},{"issue":"10","key":"58_CR22","doi-asserted-by":"publisher","first-page":"1484","DOI":"10.1016\/j.neunet.2009.05.011","volume":"22","author":"P Wawrzy\u0144ski","year":"2009","unstructured":"Wawrzy\u0144ski, P.: Real-time reinforcement learning by sequential actor-critics and experience replay. Neural Netw. 22(10), 1484\u20131497 (2009)","journal-title":"Neural Netw."},{"key":"58_CR23","doi-asserted-by":"crossref","unstructured":"Hou, Y., Liu, L., Wei, Q., Xu, X., Chen, C.: A novel DDPG method with prioritized experience replay. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 316\u2013321. IEEE (2017)","DOI":"10.1109\/SMC.2017.8122622"},{"key":"58_CR24","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. arXiv preprint arXiv:1803.00933 (2018)"},{"issue":"5","key":"58_CR25","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1093\/bioinformatics\/btt022","volume":"29","author":"G Sauthoff","year":"2013","unstructured":"Sauthoff, G., Mhl, M., Janssen, S., Giegerich, R.: Bellmans GAP a language and compiler for dynamic programming in sequence analysis. Bioinformatics 29(5), 551\u2013560 (2013)","journal-title":"Bioinformatics"}],"container-title":["Communications in Computer and Information Science","Computer Supported Cooperative Work and Social Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-15-1377-0_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,4]],"date-time":"2022-10-04T21:09:34Z","timestamp":1664917774000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-981-15-1377-0_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9789811513763","9789811513770"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-15-1377-0_58","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"14 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ChineseCSCW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Conference on Computer Supported Cooperative Work and Social Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kunming","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"16 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"chinesecscw2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.scholat.com\/confweb\/CCSCW2019","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}