{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:22:06Z","timestamp":1725798126724},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319092737"},{"type":"electronic","value":"9783319092744"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-09274-4_18","type":"book-chapter","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T03:52:06Z","timestamp":1406519526000},"page":"186-195","source":"Crossref","is-referenced-by-count":1,"title":["Intelligence as Inference or Forcing Occam on the World"],"prefix":"10.1007","author":[{"given":"Peter","family":"Sunehag","sequence":"first","affiliation":[]},{"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: NIPS 2007. MIT Press (2007)","DOI":"10.7551\/mitpress\/7503.003.0024"},{"issue":"10","key":"18_CR2","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.tics.2012.08.006","volume":"16","author":"M. Botvinick","year":"2012","unstructured":"Botvinick, M., Toussaint, M.: Planning as inference. Trends in Cognitive Sciences\u00a016(10), 485\u2013488 (2012)","journal-title":"Trends in Cognitive Sciences"},{"issue":"2","key":"18_CR3","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1162\/neco.1997.9.2.271","volume":"9","author":"P. Dayan","year":"1997","unstructured":"Dayan, P., Hinton, G.: Using expectation-maximization for reinforcement learning. Neural Computation\u00a09(2), 271\u2013278 (1997)","journal-title":"Neural Computation"},{"key":"18_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A. Dempster","year":"1977","unstructured":"Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. of the Royal Stat. Soc.: B\u00a039, 1\u201338 (1977)","journal-title":"J. of the Royal Stat. Soc.: B"},{"issue":"40","key":"18_CR5","doi-asserted-by":"publisher","first-page":"13326","DOI":"10.1523\/JNEUROSCI.6249-09.2010","volume":"30","author":"N. Fremaux","year":"2010","unstructured":"Fremaux, N., Sprekeler, H., Gerstner, W.: Functional requirements for reward-modulated spike timing-dependent plasticity. Journal of Neuroscience\u00a030(40), 13326\u201313337 (2010)","journal-title":"Journal of Neuroscience"},{"key":"18_CR6","unstructured":"Hawkins, J., Blakeslee, S.: On Intelligence. Times Books (2004)"},{"key":"18_CR7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1901\/jeab.1970.13-243","volume":"13","author":"R.J. Herrnstein","year":"1970","unstructured":"Herrnstein, R.J.: On the law of effect. Journal of the Experimental Analysis of Behavior\u00a013, 243\u2013266 (1970)","journal-title":"Journal of the Experimental Analysis of Behavior"},{"issue":"7","key":"18_CR8","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"G. Hinton","year":"2006","unstructured":"Hinton, G., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput.\u00a018(7), 1527\u20131554 (2006)","journal-title":"Neural Comput."},{"key":"18_CR9","doi-asserted-by":"crossref","DOI":"10.1007\/b138233","volume-title":"Universal Articial Intelligence: Sequential Decisions based on Algorithmic Probability","author":"M. Hutter","year":"2005","unstructured":"Hutter, M.: Universal Articial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2005)"},{"key":"18_CR10","unstructured":"Kahneman, D.: Thinking, fast and slow (2011)"},{"key":"18_CR11","unstructured":"Lenat, D.: The plausible mutation of DNA. Technical report. Standford University (1980)"},{"key":"18_CR12","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s11023-007-9079-x","volume":"17","author":"S. Legg","year":"2007","unstructured":"Legg, S., Hutter, M.: Universal Intelligence: A defintion of machine intelligence. Mind and Machine\u00a017, 391\u2013444 (2007)","journal-title":"Mind and Machine"},{"key":"18_CR13","unstructured":"Legenstein, R., Pecevski, D., Maass, W.: Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticity. In: NIPS (2007)"},{"issue":"41","key":"18_CR14","doi-asserted-by":"publisher","first-page":"15224","DOI":"10.1073\/pnas.0505220103","volume":"103","author":"Y. Loewenstein","year":"2006","unstructured":"Loewenstein, Y., Seung, S.: Operant matching is a generic outcome of synaptic plasticity based on the covariance between reward and neural activity. PNAS\u00a0103(41), 15224\u201315229 (2006)","journal-title":"PNAS"},{"key":"18_CR15","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-642-35506-6_22","volume-title":"Artificial General Intelligence","author":"L. Orseau","year":"2012","unstructured":"Orseau, L., Ring, M.: Space-time embedded intelligence. In: Bach, J., Goertzel, B., Ikl\u00e9, M. (eds.) AGI 2012. LNCS (LNAI), vol.\u00a07716, pp. 209\u2013218. Springer, Heidelberg (2012)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Pelikan, M.: Probabilistic model-building genetic algorithms. In: GECCO, pp. 777\u2013804. ACM (2012)","DOI":"10.1145\/2330784.2330916"},{"key":"18_CR17","volume-title":"Artificial Intelligence: A Modern Approach","author":"S.J. Russell","year":"2010","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice-Hall, Englewood Cliffs (2010)","edition":"3"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Russell, S.: Rationality and intelligence. Artificial Intelligence (1997)","DOI":"10.1016\/S0004-3702(97)00026-X"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: G\u00f6del machines: Fully self-referential optimal universal self-improvers. In: Artificial General Intelligence, pp. 199\u2013226 (2007)","DOI":"10.1007\/978-3-540-68677-4_7"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Sunehag, P., Hutter, M.: Optimistic agents are asymptotically optimal. In: Proceedings of the 25th Australasian AI Conference, pp. 15\u201326 (2012)","DOI":"10.1007\/978-3-642-35101-3_2"},{"key":"18_CR21","series-title":"LNAI","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-642-35506-6_32","volume-title":"Artificial General Intelligence","author":"P. Sunehag","year":"2012","unstructured":"Sunehag, P., Hutter, M.: Optimistic AIXI. In: Bach, J., Goertzel, B., Ikl\u00e9, M. (eds.) AGI 2012. LNCS (LNAI), vol.\u00a07716, pp. 312\u2013321. Springer, Heidelberg (2012)"},{"issue":"0","key":"18_CR22","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.conb.2013.12.004","volume":"25","author":"H. Shteingart","year":"2014","unstructured":"Shteingart, H., Loewenstein, Y.: Reinforcement learning and human behavior. Current Opinion in Neurobiology\u00a025(0), 93\u201398 (2014)","journal-title":"Current Opinion in Neurobiology"},{"key":"18_CR23","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1023\/A:1007383707642","volume":"28","author":"J. Schmidhuber","year":"1997","unstructured":"Schmidhuber, J., Zhao, J., Wiering, M.: Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning\u00a028, 105\u2013130 (1997)","journal-title":"Machine Learning"},{"key":"18_CR24","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195122343.001.0001","volume-title":"Developmental Plasticity and Evolution","author":"M.J. West-Eberhard","year":"2003","unstructured":"West-Eberhard, M.J.: Developmental Plasticity and Evolution. Oxford University Press, USA (2003)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Webb, G.: Occam\u2019s razor. In: Encl. of Machine Learning, Springer (2010)","DOI":"10.1007\/978-0-387-30164-8_609"},{"key":"18_CR26","unstructured":"Wingate, D., Goodman, N., Kaelbling, L., Roy, D., Tenenbaum, J.: Bayesian policy search with policy priors. IJCAI, 1565\u20131570 (2011)"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09274-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T13:20:21Z","timestamp":1717161621000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-09274-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319092737","9783319092744"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09274-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}