{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:02:01Z","timestamp":1743123721304,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030033972"},{"type":"electronic","value":"9783030033989"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-03398-9_48","type":"book-chapter","created":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T13:12:41Z","timestamp":1541077961000},"page":"562-573","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Episode-Experience Replay Based Tree-Backup Method for Off-Policy Actor-Critic Algorithm"],"prefix":"10.1007","author":[{"given":"Haobo","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Jianjun","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,2]]},"reference":[{"key":"48_CR1","unstructured":"Anschel, O., Baram, N., Shimkin, N.: Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning. arXiv preprint arXiv:1611.01929 (2016)"},{"key":"48_CR2","unstructured":"Degris, T., White, M., Sutton, R.S.: Off-policy actor-critic. CoRR abs\/1205.4839 (2012). http:\/\/arxiv.org\/abs\/1205.4839"},{"key":"48_CR3","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. arXiv preprint arXiv:1802.09477 (2018)"},{"key":"48_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/978-3-319-46379-7_21","volume-title":"Algorithmic Learning Theory","author":"A Harutyunyan","year":"2016","unstructured":"Harutyunyan, A., Bellemare, M.G., Stepleton, T., Munos, R.: Q($$\\lambda $$) with off-policy corrections. In: Ortner, R., Simon, H.U., Zilles, S. (eds.) ALT 2016. LNCS (LNAI), vol. 9925, pp. 305\u2013320. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46379-7_21"},{"key":"48_CR5","unstructured":"Hasselt, H.V.: Double Q-learning. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems 23, pp. 2613\u20132621. Curran Associates Inc. (2010). http:\/\/papers.nips.cc\/paper\/3964-double-q-learning.pdf"},{"key":"48_CR6","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"48_CR7","unstructured":"Lin, L.J.: Reinforcement learning for robots using neural networks. Technical report. School of Computer Science, Carnegie-Mellon University, Pittsburgh, PA (1993)"},{"key":"48_CR8","unstructured":"Mahmood, A.R., van Hasselt, H.P., Sutton, R.S.: Weighted importance sampling for off-policy learning with linear function approximation. In: Advances in Neural Information Processing Systems, pp. 3014\u20133022 (2014)"},{"key":"48_CR9","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"48_CR10","unstructured":"Munos, R., Stepleton, T., Harutyunyan, A., Bellemare, M.: Safe and efficient off-policy reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 1054\u20131062 (2016)"},{"key":"48_CR11","unstructured":"Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: ICML, pp. 759\u2013766. Citeseer (2000)"},{"key":"48_CR12","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"48_CR13","volume-title":"Reinforcement Learning: An introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"48_CR14","unstructured":"Sutton, R.S., Singh, S., McAllester, D.: Comparing policy-gradient algorithms (2000). http:\/\/citeseerx.ist.psu.edu\/viewdoc\/download"},{"key":"48_CR15","unstructured":"Wang, Z., et al.: Sample efficient actor-critic with experience replay. arXiv preprint arXiv:1611.01224 (2016)"},{"issue":"3\u20134","key":"48_CR16","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":"48_CR17","series-title":"The Springer International Series in Engineering and Computer Science (Knowledge Representation, Learning and Expert Systems)","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-1-4615-3618-5_2","volume-title":"Reinforcement Learning","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. In: Sutton, R.S. (ed.) Reinforcement Learning. SECS, vol. 173, pp. 5\u201332. Springer, Boston (1992). https:\/\/doi.org\/10.1007\/978-1-4615-3618-5_2"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03398-9_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T01:22:01Z","timestamp":1698801721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03398-9_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030033972","9783030033989"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03398-9_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"2 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prcv.qyhw.net.cn\/?lang=en&meeting_id=255","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}