{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:02:12Z","timestamp":1725796932516},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319088631"},{"type":"electronic","value":"9783319088648"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-08864-8_17","type":"book-chapter","created":{"date-parts":[[2014,7,8]],"date-time":"2014-07-08T09:55:33Z","timestamp":1404813333000},"page":"176-187","source":"Crossref","is-referenced-by-count":2,"title":["An Anti-hebbian Learning Rule to Represent Drive Motivations for Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Varun Raj","family":"Kompella","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sohrob","family":"Kazerounian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"17_CR1","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction, vol.\u00a01. Cambridge Univ Press (1998)"},{"key":"17_CR2","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/11840541_29","volume-title":"From Animals to Animats 9","author":"G. Konidaris","year":"2006","unstructured":"Konidaris, G., Barto, A.: An adaptive robot motivational system. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS (LNAI), vol.\u00a04095, pp. 346\u2013356. Springer, Heidelberg (2006)"},{"issue":"6","key":"17_CR3","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1177\/1059712313486817","volume":"21","author":"I. Cos","year":"2013","unstructured":"Cos, I., Ca\u00f1amero, L., Hayes, G.M., Gillies, A.: Hedonic value: Enhancing adaptation for motivated agents. Adaptive Behavior\u00a021(6), 465\u2013483 (2013)","journal-title":"Adaptive Behavior"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Woodworth, R.S.: Dynamic psychology, by Robert Sessions Woodworth. Columbia University Press (1918)","DOI":"10.7312\/wood90908"},{"key":"17_CR5","series-title":"Century psychology series","volume-title":"Principles of behavior: An introduction to behavior theory","author":"C.L. Hull","year":"1943","unstructured":"Hull, C.L.: Principles of behavior: An introduction to behavior theory. Century psychology series. D. Appleton-Century Company, Incorporated (1943)"},{"issue":"1","key":"17_CR6","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1037\/h0055810","volume":"57","author":"J. Wolpe","year":"1950","unstructured":"Wolpe, J.: Need-reduction, drive-reduction, and reinforcement: A neurophysiological view. Psychological Review\u00a057(1), 19 (1950)","journal-title":"Psychological Review"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Barrett, L., Narayanan, S.: Learning all optimal policies with multiple criteria. In: Proceedings of the 25th International Conference on Machine Learning, pp. 41\u201347. ACM (2008)","DOI":"10.1145\/1390156.1390162"},{"issue":"1","key":"17_CR8","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10994-010-5232-5","volume":"84","author":"P. Vamplew","year":"2011","unstructured":"Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical evaluation methods for multiobjective reinforcement learning algorithms. Machine Learning\u00a084(1), 51\u201380 (2011)","journal-title":"Machine Learning"},{"key":"17_CR9","unstructured":"Keramati, M., Gutkin, B.S.: A reinforcement learning theory for homeostatic regulation. In: Shawe-Taylor, J., Zemel, R.S., Bartlett, P., Pereira, F.C.N., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 24, pp. 82\u201390 (2011)"},{"issue":"1","key":"17_CR10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1177\/105971230501300101","volume":"13","author":"G.D. Konidaris","year":"2005","unstructured":"Konidaris, G.D., Hayes, G.M.: An architecture for behavior-based reinforcement learning. Adaptive Behavior\u00a013(1), 5\u201332 (2005)","journal-title":"Adaptive Behavior"},{"issue":"6","key":"17_CR11","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/S0893-6080(05)80089-9","volume":"5","author":"E. Oja","year":"1992","unstructured":"Oja, E.: Principal components, minor components, and linear neural networks. Neural Networks\u00a05(6), 927\u2013935 (1992)","journal-title":"Neural Networks"},{"issue":"7","key":"17_CR12","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1016\/j.neunet.2007.07.001","volume":"20","author":"D. Peng","year":"2007","unstructured":"Peng, D., Yi, Z., Luo, W.: Convergence analysis of a simple minor component analysis algorithm. Neural Networks\u00a020(7), 842\u2013850 (2007)","journal-title":"Neural Networks"},{"issue":"5","key":"17_CR13","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1037\/h0040934","volume":"66","author":"R.W. White","year":"1959","unstructured":"White, R.W.: Motivation reconsidered: The concept of competence. Psychological Review\u00a066(5), 297 (1959)","journal-title":"Psychological Review"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Luciw, M., Kompella, V.R., Kazerounian, S., Schmidhuber, J.: An intrinsic value system for developing multiple invariant representations with incremental slowness learning. Frontiers in Neurorobotics\u00a07 (2013)","DOI":"10.3389\/fnbot.2013.00009"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Shirinov, E., Butz, M.V.: Distinction between types of motivations: Emergent behavior with a neural, model-based reinforcement learning system. In: IEEE Symposium on Artificial Life, ALife 2009, pp. 69\u201376. IEEE (2009)","DOI":"10.1109\/ALIFE.2009.4937696"},{"key":"17_CR16","unstructured":"Sprague, N., Ballard, D.: Multiple-goal reinforcement learning with modular sarsa (0). In: IJCAI, pp. 1445\u20131447 (2003)"},{"issue":"3","key":"17_CR17","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S. Singh","year":"2000","unstructured":"Singh, S., Jaakkola, T., Littman, M.L., Szepesv\u00e1ri, C.: Convergence results for single-step on-policy reinforcement-learning algorithms. Machine Learning\u00a038(3), 287\u2013308 (2000)","journal-title":"Machine Learning"},{"key":"17_CR18","volume-title":"Reinforcement learning: An introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)"},{"key":"17_CR19","first-page":"1107","volume":"4","author":"M.G. Lagoudakis","year":"2003","unstructured":"Lagoudakis, M.G., Parr, R.: Least-squares policy iteration. The Journal of Machine Learning Research\u00a04, 1107\u20131149 (2003)","journal-title":"The Journal of Machine Learning Research"},{"issue":"16","key":"17_CR20","first-page":"2169","volume":"8","author":"S. Mahadevan","year":"2007","unstructured":"Mahadevan, S., Maggioni, M.: Proto-value functions: A laplacian framework for learning representation and control in markov decision processes. Journal of Machine Learning Research\u00a08(16), 2169\u20132231 (2007)","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"17_CR21","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TAMD.2010.2056368","volume":"2","author":"J. Schmidhuber","year":"2010","unstructured":"Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990\u20132010). IEEE Transactions on Autonomous Mental Development\u00a02(3), 230\u2013247 (2010)","journal-title":"IEEE Transactions on Autonomous Mental Development"},{"issue":"2","key":"17_CR22","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1162\/089976699300016755","volume":"11","author":"I.D. Guedalia","year":"1999","unstructured":"Guedalia, I.D., London, M., Werman, M.: An on-line agglomerative clustering method for nonstationary data. Neural Computation\u00a011(2), 521\u2013540 (1999)","journal-title":"Neural Computation"},{"issue":"11","key":"17_CR23","doi-asserted-by":"publisher","first-page":"2994","DOI":"10.1162\/NECO_a_00344","volume":"24","author":"V.R. Kompella","year":"2012","unstructured":"Kompella, V.R., Luciw, M., Schmidhuber, J.: Incremental slow feature analysis: Adaptive low-complexity slow feature updating from high-dimensional input streams. Neural Computation\u00a024(11), 2994\u20133024 (2012)","journal-title":"Neural Computation"}],"container-title":["Lecture Notes in Computer Science","From Animals to Animats 13"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-08864-8_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T03:31:50Z","timestamp":1558927910000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-08864-8_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319088631","9783319088648"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-08864-8_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}