{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T04:49:17Z","timestamp":1725598157001},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642228865"},{"type":"electronic","value":"9783642228872"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-22887-2_4","type":"book-chapter","created":{"date-parts":[[2011,7,29]],"date-time":"2011-07-29T04:00:46Z","timestamp":1311912046000},"page":"31-40","source":"Crossref","is-referenced-by-count":8,"title":["Sequential Constant Size Compressors for Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Linus","family":"Gissl\u00e9n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matt","family":"Luciw","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Graziano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"2","key":"4_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S. Amari","year":"1998","unstructured":"Amari, S.: Natural gradient works efficiently in learning. Neural Computation\u00a010(2), 251\u2013276 (1998)","journal-title":"Neural Computation"},{"key":"4_CR2","unstructured":"Anderson, C.W.: Strategy learning with multilayer connectionist representations. Technical Report TR87-509.3, GTE Labs, Waltham, MA (1987)"},{"key":"4_CR3","volume-title":"Advances in Neural Information Processing Systems","author":"B. Bakker","year":"2002","unstructured":"Bakker, B.: Reinforcement learning with Long Short-Term Memory. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems, vol.\u00a014. MIT Press, Cambridge (2002)"},{"key":"4_CR4","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"13","author":"A.G. Barto","year":"1983","unstructured":"Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics, SMC\u00a013, 834\u2013846 (1983)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, SMC"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Neural Information Processing Systems (NIPS) (2007)","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"4_CR6","volume-title":"Proc. IJCAI 1999","author":"F.J. Gomez","year":"1999","unstructured":"Gomez, F.J., Miikkulainen, R.: Solving non-Markovian control tasks with neuroevolution. In: Proc. IJCAI 1999, Denver, CO. Morgan Kaufman, San Francisco (1999)"},{"key":"4_CR7","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1007\/11871842_64","volume-title":"Machine Learning: ECML 2006","author":"F.J. Gomez","year":"2006","unstructured":"Gomez, F.J., Schmidhuber, J., Miikkulainen, R.: Efficient non-linear control through neuroevolution. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 654\u2013662. Springer, Heidelberg (2006)"},{"key":"4_CR8","unstructured":"Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. Technical Report NC-TR-96-048, NeuroCOLT (1996)"},{"issue":"2","key":"4_CR9","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1162\/106365601750190398","volume":"9","author":"N. Hansen","year":"2001","unstructured":"Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation\u00a09(2), 159\u2013195 (2001)","journal-title":"Evolutionary Computation"},{"issue":"8","key":"4_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S. Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation\u00a09(8), 1735\u20131780 (1997)","journal-title":"Neural Computation"},{"key":"4_CR11","volume-title":"Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability","author":"M. Hutter","year":"2004","unstructured":"Hutter, M.: Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2004); (On J. Schmidhuber\u2019s SNF grant 20-61847)"},{"key":"4_CR12","first-page":"860","volume":"3","author":"J.F. Kolen","year":"1991","unstructured":"Kolen, J.F., Pollack, J.B.: Back propagation is sensitive to initial conditions. Advances in neural information processing systems\u00a03, 860\u2013867 (1991)","journal-title":"Advances in neural information processing systems"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Lange, S., Riedmiller, M.: Deep Auto-Encoder Neural Networks in Reinforcement Learning. IJCNN (2010)","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"4_CR14","first-page":"11","volume":"22","author":"D.E. Moriarty","year":"1996","unstructured":"Moriarty, D.E., Miikkulainen, R.: Efficient reinforcement learning through symbiotic evolution. Machine Learning\u00a022, 11\u201332 (1996)","journal-title":"Machine Learning"},{"issue":"1-2","key":"4_CR15","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/0004-3702(90)90005-K","volume":"46","author":"J.B. Pollack","year":"1990","unstructured":"Pollack, J.B.: Recursive distributed representations. Artificial Intelligence\u00a046(1-2), 77\u2013105 (1990)","journal-title":"Artificial Intelligence"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Saravanan, N., Fogel, D.B.: Evolving neural control systems. IEEE Expert, 23\u201327 (June 1995)","DOI":"10.1109\/64.393139"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Schaul, T., Glasmachers, T., Schmidhuber, J.: High dimensions and heavy tails for natural evolution strategies. In: Genetic and Evolutionary Computation Conference (GECCO) (2011)","DOI":"10.1145\/2001576.2001692"},{"issue":"4","key":"4_CR18","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1080\/09540098908915650","volume":"1","author":"J. Schmidhuber","year":"1989","unstructured":"Schmidhuber, J.: A local learning algorithm for dynamic feedforward and recurrent networks. Connection Science\u00a01(4), 403\u2013412 (1989)","journal-title":"Connection Science"},{"key":"4_CR19","unstructured":"Schmidhuber, J.: Recurrent networks adjusted by adaptive critics. In: Proc. IEEE\/INNS International Joint Conference on Neural Networks, Washington, D. C, vol.\u00a01, pp. 719\u2013722 (1990)"},{"key":"4_CR20","first-page":"500","volume-title":"Advances in Neural Information Processing Systems, (NIPS)","author":"J. Schmidhuber","year":"1991","unstructured":"Schmidhuber, J.: Reinforcement learning in Markovian and non-Markovian environments. In: Lippman, D.S., Moody, J.E., Touretzky, D.S. (eds.) Advances in Neural Information Processing Systems (NIPS), vol.\u00a03, pp. 500\u2013506. Morgan Kaufmann, San Francisco (1991)"},{"key":"4_CR21","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1162\/106365602320169811","volume":"10","author":"K.O. Stanley","year":"2002","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation\u00a010, 99\u2013127 (2002)","journal-title":"Evolutionary Computation"},{"key":"4_CR22","volume-title":"Reinforcement learning: An introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)"},{"key":"4_CR23","first-page":"1057","volume-title":"Advances in Neural Information Processing Systems","author":"R.S. Sutton","year":"2000","unstructured":"Sutton, R.S., Mcallester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, vol.\u00a012, pp. 1057\u20131063. MIT Press, Cambridge (2000)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Werbos, P.J.: Neural networks for control and system identification. In: Proceedings of IEEE\/CDC Tampa, Florida (1989)","DOI":"10.1109\/CDC.1989.70114"},{"key":"4_CR25","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1007\/978-3-540-74958-5_43","volume-title":"Machine Learning: ECML 2007","author":"D. Wierstra","year":"2007","unstructured":"Wierstra, D., Schmidhuber, J.: Policy gradient critics. In: Kok, J.N., Koronacki, J., Lopez de Mantaras, R., Matwin, S., Mladeni\u010d, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol.\u00a04701, pp. 466\u2013477. Springer, Heidelberg (2007)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Wierstra, D., Schaul, T., Peters, J., Schmidhuber, J.: Natural evolution strategies. In: Congress on Evolutionary Computation CEC (2008)","DOI":"10.1109\/CEC.2008.4631255"},{"key":"4_CR27","first-page":"203","volume":"4","author":"X. Yao","year":"1993","unstructured":"Yao, X.: Xin Yao. A review of evolutionary artificial neural networks. International Journal of Intelligent Systems\u00a04, 203\u2013222 (1993)","journal-title":"International Journal of Intelligent Systems"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-22887-2_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T10:39:27Z","timestamp":1712659167000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-22887-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642228865","9783642228872"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-22887-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}