{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:36:49Z","timestamp":1726043809530},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030304867"},{"type":"electronic","value":"9783030304874"}],"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\/978-3-030-30487-4_46","type":"book-chapter","created":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:02:47Z","timestamp":1567969367000},"page":"598-610","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Recurrent Policy Networks for Planning Under Partial Observability"],"prefix":"10.1007","author":[{"given":"Zixuan","family":"Chen","sequence":"first","affiliation":[]},{"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"issue":"1-2","key":"46_CR1","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/0004-3702(96)00007-0","volume":"82","author":"Nils J. Nilsson","year":"1996","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence - A Modern Approach, 2nd Edn. Prentice Hall (2003). \n                      https:\/\/doi.org\/10.1016\/0004-3702(96)00007-0","journal-title":"Artificial Intelligence"},{"key":"46_CR2","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1613\/jair.1659","volume":"24","author":"MTJ Spaan","year":"2005","unstructured":"Spaan, M.T.J., Vlassis, N.A.: Perseus: randomized point-based value iteration for POMDPs. J. Artif. Intell. Res. 24, 195\u2013220 (2005). \n                      https:\/\/doi.org\/10.1613\/jair.1659","journal-title":"J. Artif. Intell. Res."},{"key":"46_CR3","unstructured":"Karkus, P., Hsu, D., Lee, W.S.: QMDP-Net: deep learning for planning under partial observability. In: 30th Advances Neural Information Processing Systems (NIPS), pp. 4697\u20134707. arXiv preprint \n                      arXiv:1703.06692\n                      \n                     (2017)"},{"key":"46_CR4","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1287\/opre.26.2.282","volume":"26","author":"EJ Sondik","year":"1978","unstructured":"Sondik, E.J.: The optimal control of partially observable markov processes over the infinite horizon: discounted costs. Oper. Res. 26, 282\u2013304 (1978). \n                      https:\/\/doi.org\/10.1287\/opre.26.2.282","journal-title":"Oper. Res."},{"key":"46_CR5","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1287\/opre.39.1.162","volume":"39","author":"WS Lovejoy","year":"1991","unstructured":"Lovejoy, W.S.: Computationally feasible bounds for partially observed markov decision processes. Oper. Res. 39, 162\u2013175 (1991). \n                      https:\/\/doi.org\/10.1287\/opre.39.1.162","journal-title":"Oper. Res."},{"key":"46_CR6","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","volume":"101","author":"LP Kaelbling","year":"1998","unstructured":"Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artif. Intell. 101, 99\u2013134 (1998). \n                      https:\/\/doi.org\/10.1016\/S0004-3702(98)00023-X","journal-title":"Artif. Intell."},{"key":"46_CR7","doi-asserted-by":"publisher","unstructured":"Kurniawati, H., Hsu, D., Lee, W.S.: SARSOP: efficient point-based POMDP planning by approximating optimally reachable belief spaces. In: Robotics: Science and Systems (2008). \n                      https:\/\/doi.org\/10.15607\/rss.2008.iv.009","DOI":"10.15607\/rss.2008.iv.009"},{"key":"46_CR8","unstructured":"Pineau, J., Gordon, G.J., Thrun, S.: Applying metric-trees to belief-point POMDPs. In: 16th Advances Neural Information Processing Systems (NIPS), pp. 759\u2013766 (2003)"},{"key":"46_CR9","unstructured":"Silver, D., Veness, J.: Monte-carlo planning in large POMDPs. In: 24th Advances Neural Information Processing Systems (NIPS), pp. 2164\u20132172 (2010)"},{"key":"46_CR10","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1613\/jair.5328","volume":"58","author":"N Ye","year":"2017","unstructured":"Ye, N., Somani, A., Hsu, D., Lee, W.S.: DESPOT: online POMDP planning with regularization. J. Artif. Intell. Res. 58, 231\u2013266 (2017). \n                      https:\/\/doi.org\/10.1613\/jair.5328","journal-title":"J. Artif. Intell. Res."},{"key":"46_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/bf02591967","volume":"27","author":"DP Bertsekas","year":"1983","unstructured":"Bertsekas, D.P.: Distributed asynchronous computation of fixed points. Math. Program. 27, 107\u2013120 (1983). \n                      https:\/\/doi.org\/10.1007\/bf02591967","journal-title":"Math. Program."},{"key":"46_CR12","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/B978-1-55860-377-6.50052-9","volume-title":"Machine Learning Proceedings 1995","author":"Michael L. Littman","year":"1995","unstructured":"Littman, M.L., Cassandra, A.R., Kaelbling, L.P.: Learning policies for partially observable environments: scaling up. In: 12th International Conference on Machine Learning (ICML), pp. 362\u2013370 (1995). \n                      https:\/\/doi.org\/10.1016\/b978-1-55860-377-6.50052-9"},{"key":"46_CR13","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"46_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/978-3-030-04179-3_15","volume-title":"Neural Information Processing","author":"Z Pan","year":"2018","unstructured":"Pan, Z., Zhang, Z., Chen, Z.: Asynchronous value iteration network. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11302, pp. 169\u2013180. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-030-04179-3_15"},{"issue":"1","key":"46_CR15","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/bf00993104","volume":"13","author":"Andrew W. Moore","year":"1993","unstructured":"Moore, A.W., Atkeson, C.G.: Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn., 103\u2013130 (1993). \n                      https:\/\/doi.org\/10.1007\/bf00993104","journal-title":"Machine Learning"},{"key":"46_CR16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/0004-3702(94)00011-O","volume":"72","author":"AG Barto","year":"1995","unstructured":"Barto, A.G., Bradtke, S.J., Singh, S.P.: Learning to act using real-time dynamic programming. Artif. Intell. 72, 81\u2013138 (1995). \n                      https:\/\/doi.org\/10.1016\/0004-3702(94)00011-O","journal-title":"Artif. Intell."},{"key":"46_CR17","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: 4th International Conference on Learning Representations (ICLR). arXiv preprint \n                      arXiv:1511.05952\n                      \n                     (2016)"},{"key":"46_CR18","unstructured":"Aviv, T., Yi, W., Garrett, T., Sergey, L., Pieter, A.: Value iteration networks. In: 29th Advances in Neural Information Processing Systems (NIPS), pp. 2154\u20132162 (2016)"},{"key":"46_CR19","unstructured":"Oh, J., Singh, S., Lee, H.: Value prediction network. In: 30th Advances in Neural Information Processing Systems (NIPS), pp. 6120\u20136130 (2017)"},{"key":"46_CR20","doi-asserted-by":"publisher","unstructured":"Gupta, S., Davidson, J., Levine, S., Sukthankar, R., Malik, J.: Cognitive mapping and planning for visual navigation. In: 35th Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7272\u20137281 (2017). \n                      https:\/\/doi.org\/10.1109\/cvpr.2017.769","DOI":"10.1109\/cvpr.2017.769"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Theoretical Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30487-4_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,8]],"date-time":"2019-09-08T19:16:02Z","timestamp":1567970162000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-30487-4_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304867","9783030304874"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30487-4_46","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":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}