{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:26:26Z","timestamp":1725549986053},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540294146"},{"type":"electronic","value":"9783540320852"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11569596_54","type":"book-chapter","created":{"date-parts":[[2005,11,15]],"date-time":"2005-11-15T06:17:55Z","timestamp":1132035475000},"page":"512-523","source":"Crossref","is-referenced-by-count":1,"title":["ARKAQ-Learning: Autonomous State Space Segmentation and Policy Generation"],"prefix":"10.1007","author":[{"given":"Alp","family":"Sarda\u011f","sequence":"first","affiliation":[]},{"given":"H. Levent","family":"Ak\u0131n","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"54_CR1","unstructured":"Boyen, X., Koller, D.: Tractable inference for complex stochastic processes. In: Conference on Uncertainty in Artificial Intelligence, pp. 33\u201342 (1998)"},{"key":"54_CR2","first-page":"1050","volume-title":"Neural Information Processing Systems","author":"B. Sallans","year":"2000","unstructured":"Sallans, B.: Learning factored representations on partially observable Markov decision process. In: Neural Information Processing Systems, pp. 1050\u20131056. MIT Press, Cambridge (2000)"},{"key":"54_CR3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. Kaelbling","year":"1996","unstructured":"Kaelbling, L., Littman, M., Moore, A.: Reinforcement Learning: A Survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"54_CR4","unstructured":"Watkins, C.J.: Learning with delayed rewards. PhD Thesis, Cambridge University (1989)"},{"key":"54_CR5","doi-asserted-by":"crossref","unstructured":"Singh, S., Jaakkola, T., Jordan, M.: Learning without state estimation in partially observable Markov decision processes. In: International Conference on Machine Learning, pp. 284\u2013292 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50042-8"},{"key":"54_CR6","first-page":"387","volume-title":"Proceedings of the Twelfth International Conference on Machine Learning","author":"R.A. McCallum","year":"1995","unstructured":"McCallum, R.A.: Instance-based util distinctions for reinforcement learning with hidden state. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 387\u2013395. Morgan Kaufmann, San Francisco (1995)"},{"key":"54_CR7","unstructured":"Lin, L., Mitchell, T.M.: Memory approaches to reinforcement learning in non-Markovian domains. Technical Report CMU-CS-92-138, School of Computer Science, Carnegie Mellon University (1992)"},{"key":"54_CR8","doi-asserted-by":"crossref","unstructured":"Rumelhart, D., Hinton, G., Williams, R.: Parallel distributed processing. In: Learning internal representations by error propagation, ch.\u00a08. MIT Press, Cambridge (1986)","DOI":"10.21236\/ADA164453"},{"key":"54_CR9","first-page":"80","volume-title":"Kalman Filtering","author":"A. Grewal","year":"1993","unstructured":"Grewal, A., Andrews, C.: Kalman Filtering, pp. 80\u2013102. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"54_CR10","first-page":"1","volume-title":"Stochastic models, estimation and control","author":"P.S. Maybeck","year":"1979","unstructured":"Maybeck, P.S.: Stochastic models, estimation and control, vol.\u00a01, pp. 1\u201315. Academic Press, London (1979)"},{"key":"54_CR11","doi-asserted-by":"crossref","unstructured":"Carpenter, G.A., Grossberg, S.: ART2. Self-Organization of Stable Category Recognition Codes for Analog Input Patterns. Applied Optics, 4919\u20134930 (1989)","DOI":"10.1117\/12.942747"},{"key":"54_CR12","first-page":"493","volume-title":"Neural Networks","author":"G.A. Carpenter","year":"1991","unstructured":"Carpenter, G.A., Grossberg, S., Rosen, D.B.: ART 2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition. In: Neural Networks, vol.\u00a04, pp. 493\u2013504. Pergamon Press, Oxford (1991)"},{"key":"54_CR13","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"54_CR14","volume-title":"ynamic Programming: Deterministic and Stochastic Models","author":"D. Bertsekas","year":"1987","unstructured":"Bertsekas, D.: ynamic Programming: Deterministic and Stochastic Models. Prentice-Hall, Englewood Cliffs (1987)"},{"key":"54_CR15","volume-title":"Dynamic Programming and Markov Processes","author":"R.A. Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. The MIT Press, Cambridge (1960)"},{"key":"54_CR16","first-page":"1066","volume-title":"Proceedings of Neural Information Processings Systems","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Singh, S., Precup, D., Ravindran, B.: Improved switching among temporally abstract actions. In: Proceedings of Neural Information Processings Systems, pp. 1066\u20131072. MIT Press, Cambridge (1999)"},{"key":"54_CR17","unstructured":"Peshkin, L., Shelton, H.: Learning from scarce experience. In: Proceedings of the Nineteenth International Conference on Machine Learning, pp. 498\u2013505 (2002)"},{"key":"54_CR18","unstructured":"Peshkin, L., Meuleau, N., Kaelbling, L.P.: Learning Policies with External Memory. In: Proceedings of the Sixteenth International Conference on Machine Learning, pp. 307\u2013314 (1999)"},{"key":"54_CR19","doi-asserted-by":"crossref","unstructured":"Tesauro, G.: Programming Backgammon Using Self-Teaching Neural Nets. Artificial Intelligence, 181\u2013199 (2002)","DOI":"10.1016\/S0004-3702(01)00110-2"},{"key":"54_CR20","doi-asserted-by":"crossref","unstructured":"Carpenter, G.A., Grossberg, S.: A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing, 3754 (1987)","DOI":"10.1016\/S0734-189X(87)80014-2"}],"container-title":["Lecture Notes in Computer Science","Computer and Information Sciences - ISCIS 2005"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11569596_54.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T19:55:18Z","timestamp":1605642918000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11569596_54"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540294146","9783540320852"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/11569596_54","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}