{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:06:19Z","timestamp":1725807979102},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319126425"},{"type":"electronic","value":"9783319126432"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-12643-2_37","type":"book-chapter","created":{"date-parts":[[2014,10,22]],"date-time":"2014-10-22T02:58:17Z","timestamp":1413946697000},"page":"300-307","source":"Crossref","is-referenced-by-count":2,"title":["Stochastic Decision Making in Learning Classifier Systems through a Natural Policy Gradient Method"],"prefix":"10.1007","author":[{"given":"Gang","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoning","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colin","family":"Douch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"2","key":"37_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"},{"issue":"11","key":"37_CR2","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1016\/j.automatica.2009.07.008","volume":"45","author":"S. Bhatnagar","year":"2009","unstructured":"Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Natural actor-critic algorithms. Journal Automatica\u00a045(11), 2471\u20132482 (2009)","journal-title":"Journal Automatica"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Butz, M.V., Goldberg, D.E., Lanzi, P.L.: Gradient descent methods in learning classifier systems: improving xcs performance in multistep problems. IEEE Transactions on Evolutionary Computation (2005)","DOI":"10.1109\/TEVC.2005.850265"},{"key":"37_CR4","series-title":"Lecture Notes in Artificial Intelligence","first-page":"253","volume-title":"Advances in Learning Classifier Systems","author":"M.V. Butz","year":"2002","unstructured":"Butz, M.V., Wilson, S.W.: An Algorithmic Description of XCS. In: Lanzi, P.L., Stolzmann, W., Wilson, S.W. (eds.) IWLCS 2001. LNCS (LNAI), vol.\u00a02321, pp. 253\u2013272. Springer, Heidelberg (2002)"},{"key":"37_CR5","unstructured":"Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Holland, J.H.: Adaptation. In: Progress in Theoretical Biology, vol.\u00a04, pp. 263\u2013293. Academic Press (1976)","DOI":"10.1016\/B978-0-12-543104-0.50012-3"},{"key":"37_CR7","unstructured":"Lanzi, P.L.: An analysis of the memory mechanism of xcsm. In: Proceedings of the Third Genetic Programming Conference, pp. 643\u2013651 (1998)"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Lanzi, P.L.: Learning classifier systems: then and now. Evolutionary Intelligence (2008)","DOI":"10.1007\/s12065-007-0003-3"},{"key":"37_CR9","unstructured":"Lanzi, P.L., Colombetti, M.: An extension to the xcs classifier system for stochastic environments. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 353\u2013360 (2000)"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Peters, J., Schaal, S.: Natural actor-critic. Neurocomputing, 1180\u20131190 (2008)","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"37_CR12","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 12 (NIPS 1999), vol.\u00a012, pp. 1057\u20131063. MIT Press (2000)"},{"issue":"2","key":"37_CR13","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1162\/evco.1995.3.2.149","volume":"3","author":"S.W. Wilson","year":"1995","unstructured":"Wilson, S.W.: Classifier fitness based on accuracy. Evolutionary Computation\u00a03(2), 149\u2013175 (1995)","journal-title":"Evolutionary Computation"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-12643-2_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,28]],"date-time":"2019-05-28T06:46:49Z","timestamp":1559026009000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-12643-2_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319126425","9783319126432"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-12643-2_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}