iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://api.crossref.org/works/10.1007/978-3-642-33269-2_56
{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T15:30:33Z","timestamp":1725895833816},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642332685"},{"type":"electronic","value":"9783642332692"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33269-2_56","type":"book-chapter","created":{"date-parts":[[2012,9,18]],"date-time":"2012-09-18T18:55:50Z","timestamp":1347994550000},"page":"443-450","source":"Crossref","is-referenced-by-count":3,"title":["Biologically Plausible Multi-dimensional Reinforcement Learning in Neural Networks"],"prefix":"10.1007","author":[{"given":"Jaldert O.","family":"Rombouts","sequence":"first","affiliation":[]},{"given":"Arjen","family":"van Ooyen","sequence":"additional","affiliation":[]},{"given":"Pieter R.","family":"Roelfsema","sequence":"additional","affiliation":[]},{"given":"Sander M.","family":"Bohte","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"56_CR1","unstructured":"Bellman, R.E.: Dynamic Programming. Princeton Univ. Press (1957)"},{"key":"56_CR2","doi-asserted-by":"crossref","unstructured":"Bishop, C.M.: Neural networks for pattern recognition. Oxford Univ. Press (1995)","DOI":"10.1201\/9781420050646.ptb6"},{"key":"56_CR3","unstructured":"Chang, Y.H., Ho, T., Kaelbling, L.P.: All learning is local: Multi-agent learning in global reward games. In: NIPS, vol.\u00a016 (2004)"},{"issue":"43","key":"56_CR4","doi-asserted-by":"publisher","first-page":"13524","DOI":"10.1523\/JNEUROSCI.2469-09.2009","volume":"29","author":"S.J. Gershman","year":"2009","unstructured":"Gershman, S.J., Pesaran, B., Daw, N.D.: Human reinforcement learning subdivides structured action spaces by learning effector-specific values. J. Neurosci.\u00a029(43), 13524\u201313531 (2009)","journal-title":"J. Neurosci."},{"key":"56_CR5","doi-asserted-by":"crossref","unstructured":"Ring, M., Schaul, T., Schmidhuber, J.: The Two-Dimensional Organization of Behavior. In: IEEE ICDL, pp. 1\u20138 (2011)","DOI":"10.1109\/DEVLRN.2011.6037326"},{"issue":"17","key":"56_CR6","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1162\/0899766054615699","volume":"2214","author":"P.R. Roelfsema","year":"2005","unstructured":"Roelfsema, P.R., van Ooyen, A.: Attention-Gated Reinforcement Learning of Internal Representations for Classification. Neural Comput.\u00a02214(17), 2176\u20132214 (2005)","journal-title":"Neural Comput."},{"issue":"2","key":"56_CR7","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.tics.2009.11.005","volume":"14","author":"P.R. Roelfsema","year":"2010","unstructured":"Roelfsema, P.R., van Ooyen, A., Watanabe, T.: Perceptual learning rules based on reinforcers and attention. Trends Cogn. Sci.\u00a014(2), 64\u201371 (2010)","journal-title":"Trends Cogn. Sci."},{"key":"56_CR8","first-page":"1","volume":"1","author":"C.A. Rothkopf","year":"2010","unstructured":"Rothkopf, C.A., Ballard, D.H.: Credit Assignment in Multiple Goal Embodied Visuomotor Behavior. Front. Psych.\u00a01, 1\u201313 (2010)","journal-title":"Front. Psych."},{"issue":"9","key":"56_CR9","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"D.E. Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature\u00a0323(9), 533\u2013536 (1986)","journal-title":"Nature"},{"issue":"5306","key":"56_CR10","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","volume":"275","author":"W. Schultz","year":"1997","unstructured":"Schultz, W., Dayan, P., Montague, P.R.: A neural substrate of prediction and reward. Science\u00a0275(5306), 1593\u20131599 (1997)","journal-title":"Science"},{"key":"56_CR11","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning. MIT Press (1998)"},{"issue":"2","key":"56_CR12","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1177\/105971239700600202","volume":"6","author":"M. Wiering","year":"1997","unstructured":"Wiering, M., Schmidhuber, J.: HQ-Learning. Adapt. Behav.\u00a06(2), 219\u2013246 (1997)","journal-title":"Adapt. Behav."},{"issue":"3-4","key":"56_CR13","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"R.J. Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn.\u00a08(3-4), 229\u2013256 (1992)","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33269-2_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,7]],"date-time":"2019-05-07T11:57:13Z","timestamp":1557230233000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33269-2_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642332685","9783642332692"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33269-2_56","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}