{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T21:31:19Z","timestamp":1767648679754,"version":"3.38.0"},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540231059"},{"type":"electronic","value":"9783540301158"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-30115-8_33","type":"book-chapter","created":{"date-parts":[[2010,9,18]],"date-time":"2010-09-18T03:24:16Z","timestamp":1284780256000},"page":"347-358","source":"Crossref","is-referenced-by-count":27,"title":["Sparse Distributed Memories for On-Line Value-Based Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Bohdana","family":"Ratitch","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doina","family":"Precup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"33_CR1","unstructured":"Anderson, C.: Q-learning with hidden-unit restarting. In: NIPS, pp. 81\u201388 (1993)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning. Artificial Intelligence Review, 11\u201373 (1997)","DOI":"10.1023\/A:1006559212014"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning for control. Artificial Intelligence Review, 75\u2013113 (1997)","DOI":"10.1023\/A:1006511328852"},{"key":"33_CR4","unstructured":"Blanzieri, E., Katenkamp, P.: Learning RBFNs on-line. In: ICML, pp. 37\u201345 (1996)"},{"key":"33_CR5","unstructured":"Dietterich, T.G., Wang, X.: Batch value function approximation via support vectors. In: NIPS, pp. 444\u2013450 (2001)"},{"key":"33_CR6","unstructured":"Engel, Y., Mannor, S., Meir, R.: Bayes meets Bellman: The Gaussian process approach to temporal difference learning. In: ICML, pp. 154\u2013161 (2003)"},{"key":"33_CR7","unstructured":"Flachs, B., Flynn, J.M.: Sparse adaptive memory (Tech. Rep. 92-530). Computer Systems Lab., Dptm. of Electrical Engineering and Computer Science, Stanford University (1992)"},{"key":"33_CR8","unstructured":"Forbes, J.R.N.: Reinforcement learning for autonomous vehicles. Ph.D. Thesis, Computer Science Department, University of California at Berkeley (2002)"},{"key":"33_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1007\/BFb0020222","volume-title":"Artificial Neural Networks - ICANN\u201997","author":"B. Fritzke","year":"1997","unstructured":"Fritzke, B.: A self-organizing network that can follow non-stationary distributions. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol.\u00a01327, pp. 613\u2013618. Springer, Heidelberg (1997)"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Gordon, G.J.: Stable function approximation in dynamic programming. In: ICML, pp. 261\u2013268 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"33_CR11","unstructured":"Gordon, G.J.: Reinforcement learning with function approximation converges to a region. In: NIPS, pp. 1040\u20131046 (2000)"},{"key":"33_CR12","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1109\/72.572115","volume":"3","author":"T.A. Hely","year":"1997","unstructured":"Hely, T.A., Willshaw, D.J., Hayes, G.M.: A new approach to Kanerva\u2019s sparse distributed memory. Neural Networks\u00a03, 791\u2013794 (1997)","journal-title":"Neural Networks"},{"key":"33_CR13","first-page":"50","volume-title":"Associative neural memories: Theory and implementation","author":"P. Kanerva","year":"1993","unstructured":"Kanerva, P.: Sparse distributed memory and related models. In: Hassoun, M. (ed.) Associative neural memories: Theory and implementation, pp. 50\u201376. Oxford University Press, Oxford (1993)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Kondo, T., Ito, K.: A reinforcement learning with adaptive state space recruitment strategy for real autonomous mobile robots. In: IROS (2002)","DOI":"10.1109\/IRDS.2002.1041504"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Kretchmar, R., Anderson, C.: Comparison of CMACs and RBFs for local function approximators in reinforcement learning. In: IEEE Int. Conf. on Neural Networks, pp. 834\u2013837 (1997)","DOI":"10.1109\/ICNN.1997.616132"},{"key":"33_CR16","unstructured":"Lagoudakis, M.G., Parr, R.: Reinforcement learning as classification: Leveraging modern classifiers. In: ICML, pp. 424\u2013431 (2003)"},{"key":"33_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/3-540-36755-1_24","volume-title":"Machine Learning: ECML 2002","author":"M. Martin","year":"2002","unstructured":"Martin, M.: On-line support vector machine regression. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol.\u00a02430, pp. 282\u2013294. Springer, Heidelberg (2002)"},{"key":"33_CR18","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1023\/A:1017992615625","volume":"49","author":"R. Munos","year":"2000","unstructured":"Munos, R., Moore, A.: Variable resolution discretization in optimal control. Machine learning\u00a049, 291\u2013323 (2000)","journal-title":"Machine learning"},{"key":"33_CR19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1162\/neco.1991.3.2.213","volume":"3","author":"J. Platt","year":"1991","unstructured":"Platt, J.: A resource-allocating network for function interpolation. Neural Computation\u00a03, 213\u2013225 (1991)","journal-title":"Neural Computation"},{"key":"33_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/3-540-44668-0_46","volume-title":"Artificial Neural Networks - ICANN 2001","author":"L. Ralaivola","year":"2001","unstructured":"Ralaivola, L., d\u2019Alche Buc, F.: Incremental support vector machine learning: a local approach. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol.\u00a02130, p. 322. Springer, Heidelberg (2001)"},{"key":"33_CR21","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1023\/A:1008810406347","volume":"5","author":"R.P.N. Rao","year":"1998","unstructured":"Rao, R.P.N., Fuentes, O.: Hierarchical learning of navigational behaviors in an autonomous robot using a predictive SDM. Autonomous Robots\u00a05, 297\u2013316 (1998)","journal-title":"Autonomous Robots"},{"key":"33_CR22","unstructured":"Ratitch, B., Mahadevan, S., Precup, D.: Sparse distribute memories as function approximators in value-based reinforcement learning: Case studies. In: AAAI Workshop on Learning and Planning in Markov Processes (2004)"},{"key":"33_CR23","unstructured":"Reynolds, S.I.: Decision boundary partitioning: variable resolution model-free reinforcement learning. In: ICML, pp. 783\u2013790 (2000)"},{"key":"33_CR24","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1177\/105971239700600201","volume":"6","author":"J.C. Santamaria","year":"1998","unstructured":"Santamaria, J.C., Sutton, R.S., Ram, A.: Experiments with reinforcement learning in problems with continuous state and action spaces. Adaptive Behavior\u00a06, 163\u2013218 (1998)","journal-title":"Adaptive Behavior"},{"key":"33_CR25","unstructured":"Scholkopf, B.: The kernel trick for distances. In: NIPS, pp. 301\u2013307 (2000)"},{"key":"33_CR26","unstructured":"Smart, W., Kaelbling, L.P.: Practical reinforcement learning in continuous spaces. In: ICML, pp. 903\u2013910 (2000)"},{"key":"33_CR27","volume-title":"Reinforcement learning. An introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning. An introduction. The MIT Press, Cambridge (1998)"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Whitehead, S.D.: Online learning with random representations. In: ICML, pp. 314\u2013321 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50047-2"},{"key":"33_CR29","unstructured":"Szepesvari, C., Smart, W.D.: Convergent value function approximation methods (2004), http:\/\/www.sztaki.hu\/~szcsaba\/papers\/szws_icml2004_rlfapp.pdf"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Feature-based methods for large scale dynamic programming. Machine Learning, 59\u201394 (1996)","DOI":"10.1007\/BF00114724"},{"key":"33_CR31","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"J.N. Tsitsiklis","year":"1997","unstructured":"Tsitsiklis, J.N., Van Roy, B.: An analysis of temporal difference learning with function approximation. IEEE Transactions on Automatic Control\u00a042, 674\u2013690 (1997)","journal-title":"IEEE Transactions on Automatic Control"},{"key":"33_CR32","unstructured":"Uther, W.T.B., Veloso, M.M.: Tree based discretization for continuous state space reinforcement learning. In: AAAI, pp. 769\u2013774 (1998)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2004"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30115-8_33.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T22:23:48Z","timestamp":1740522228000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30115-8_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540231059","9783540301158"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30115-8_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}