{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:36:16Z","timestamp":1742913376270,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319961354"},{"type":"electronic","value":"9783319961361"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-319-96136-1_16","type":"book-chapter","created":{"date-parts":[[2018,7,7]],"date-time":"2018-07-07T12:27:46Z","timestamp":1530966466000},"page":"187-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Adjacency Kanerva Coding for\u00a0Memory-Constrained Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0268-0903","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Waleed","family":"Meleis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,8]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Allen, M., Fritzsche, P.: Reinforcement learning with adaptive Kanerva coding for Xpilot game AI. In: 2011 IEEE Congress of Evolutionary Computation (CEC), pp. 1521\u20131528. IEEE (2011). https:\/\/doi.org\/10.1109\/CEC.2011.5949796","key":"16_CR1","DOI":"10.1109\/CEC.2011.5949796"},{"unstructured":"Chernova, S., Veloso, M.: Tree-based policy learning in continuous domains through teaching by demonstration. In: Proceedings of Workshop on Modeling Others from Observations (MOO 2006) (2006)","key":"16_CR2"},{"doi-asserted-by":"publisher","unstructured":"Chiariotti, F., D\u2019Aronco, S., Toni, L., Frossard, P.: Online learning adaptation strategy for dash clients. In: Proceedings of the 7th International Conference on Multimedia Systems, p. 8. ACM (2016). https:\/\/doi.org\/10.1145\/2910017.2910603","key":"16_CR3","DOI":"10.1145\/2910017.2910603"},{"unstructured":"Forbes, J.R.N.: Reinforcement Learning for Autonomous Vehicles. University of California, Berkeley (2002)","key":"16_CR4"},{"key":"16_CR5","series-title":"Cognitive Technologies","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16590-0","volume-title":"Qualitative Spatial Abstraction in Reinforcement Learning","author":"Lutz Frommberger","year":"2010","unstructured":"Frommberger, L.: Qualitative Spatial Abstraction in Reinforcement Learning. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-16590-0"},{"issue":"6","key":"16_CR6","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TNNLS.2013.2247418","volume":"24","author":"M Geist","year":"2013","unstructured":"Geist, M., Pietquin, O.: Algorithmic survey of parametric value function approximation. IEEE Trans. Neural Netw. Learn. Syst. 24(6), 845\u2013867 (2013). https:\/\/doi.org\/10.1109\/TNNLS.2013.2247418","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"doi-asserted-by":"publisher","unstructured":"Hausknecht, M., Khandelwal, P., Miikkulainen, R., Stone, P.: HyperNEAT-GGP: a hyperNEAT-based atari general game player. In: Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation, pp. 217\u2013224. ACM (2012). https:\/\/doi.org\/10.1145\/2330163.2330195","key":"16_CR7","DOI":"10.1145\/2330163.2330195"},{"unstructured":"Kanerva, P.: Sparse distributed memory and related models, vol. 92. NASA Ames Research Center, Research Institute for Advanced Computer Science (1992)","key":"16_CR8"},{"doi-asserted-by":"publisher","unstructured":"Keller, P.W., Mannor, S., Precup, D.: Automatic basis function construction for approximate dynamic programming and reinforcement learning. In: Proceedings of International Conference on Machine Learning (2006). https:\/\/doi.org\/10.1145\/1143844.1143901","key":"16_CR9","DOI":"10.1145\/1143844.1143901"},{"issue":"24","key":"16_CR10","doi-asserted-by":"publisher","first-page":"245129","DOI":"10.1103\/PhysRevB.94.245129","volume":"94","author":"L Li","year":"2016","unstructured":"Li, L., Baker, T.E., White, S.R., Burke, K.: Pure density functional for strong correlations and the thermodynamic limit from machine learning. Phys. Rev. B 94(24), 245129 (2016)","journal-title":"Phys. Rev. B"},{"doi-asserted-by":"publisher","unstructured":"Li, W., Zhou, F., Meleis, W., Chowdhury, K.: Learning-based and data-driven TCP design for memory-constrained iot. In: 2016 International Conference on Distributed Computing in Sensor Systems (DCOSS), pp. 199\u2013205. IEEE (2016). https:\/\/doi.org\/10.1109\/DCOSS.2016.8","key":"16_CR11","DOI":"10.1109\/DCOSS.2016.8"},{"unstructured":"Lin, S., Wright, R.: Evolutionary tile coding: an automated state abstraction algorithm for reinforcement learning. In: Abstraction, Reformulation, and Approximation (2010)","key":"16_CR12"},{"doi-asserted-by":"publisher","unstructured":"Mao, H., Netravali, R., Alizadeh, M.: Neural adaptive video streaming with pensieve. In: Proceedings of the Conference of the ACM Special Interest Group on Data Communication, pp. 197\u2013210. ACM (2017). https:\/\/doi.org\/10.1145\/3098822.3098843","key":"16_CR13","DOI":"10.1145\/3098822.3098843"},{"issue":"2","key":"16_CR14","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1017992615625","volume":"49","author":"R Munos","year":"2002","unstructured":"Munos, R., Moore, A.: Variable resolution discretization in optimal control. Mach. Learn. 49(2), 291\u2013323 (2002)","journal-title":"Mach. Learn."},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-540-30115-8_33","volume-title":"Machine Learning: ECML 2004","author":"B Ratitch","year":"2004","unstructured":"Ratitch, B., Precup, D.: Sparse distributed memories for on-line value-based reinforcement learning. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 347\u2013358. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-30115-8_33"},{"issue":"2","key":"16_CR16","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1177\/105971239700600201","volume":"6","author":"JC Santamar\u00eda","year":"1997","unstructured":"Santamar\u00eda, J.C., Sutton, R.S., Ram, A.: Experiments with reinforcement learning in problems with continuous state and action spaces. Adapt. Behav. 6(2), 163\u2013217 (1997)","journal-title":"Adapt. Behav."},{"unstructured":"Smart, W.D., Kaelbling, L.P.: Practical reinforcement learning in continuous spaces. In: ICML, pp. 903\u2013910 (2000)","key":"16_CR17"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. Bradford Books (1998)","key":"16_CR18","DOI":"10.1109\/TNN.1998.712192"},{"unstructured":"Whiteson, S., Taylor, M.E., Stone, P., et al.: Adaptive tile coding for value function approximation. University of Texas at Austin, Computer Science Department (2007)","key":"16_CR19"},{"doi-asserted-by":"publisher","unstructured":"Wu, C., Li, W., Meleis, W.: Rough sets-based prototype optimization in Kanerva-based function approximation. In: 2015 IEEE\/WIC\/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 2, pp. 283\u2013291. IEEE (2015). https:\/\/doi.org\/10.1109\/WI-IAT.2015.179","key":"16_CR20","DOI":"10.1109\/WI-IAT.2015.179"},{"doi-asserted-by":"publisher","unstructured":"Wu, C., Meleis, W.: Adaptive Kanerva-based function approximation for multi-agent systems. In: Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, vol. 3. pp. 1361\u20131364. International Foundation for Autonomous Agents and Multiagent Systems (2008). https:\/\/doi.org\/10.1145\/1402821.1402872","key":"16_CR21","DOI":"10.1145\/1402821.1402872"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Data Mining in Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-96136-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T17:32:49Z","timestamp":1709832769000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-96136-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319961354","9783319961361"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-96136-1_16","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":"8 July 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLDM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning and Data Mining in Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New York, NY","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"15 July 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2018","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":"mldm2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mldm.de\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}