{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T09:00:12Z","timestamp":1754557212856},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642355059"},{"type":"electronic","value":"9783642355066"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-35506-6_32","type":"book-chapter","created":{"date-parts":[[2012,12,3]],"date-time":"2012-12-03T05:00:54Z","timestamp":1354510854000},"page":"312-321","source":"Crossref","is-referenced-by-count":3,"title":["Optimistic AIXI"],"prefix":"10.1007","author":[{"given":"Peter","family":"Sunehag","sequence":"first","affiliation":[]},{"given":"Marcus","family":"Hutter","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"32_CR1","unstructured":"Asmuth, J., Li, L., Littman, M.L., Nouri, A., Wingate, D.: Pac-mdp reinforcement learning with bayesian priors (2009)"},{"issue":"3","key":"32_CR2","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1214\/aoms\/1177704456","volume":"33","author":"D. Blackwell","year":"1962","unstructured":"Blackwell, D., Dubins, L.: Merging of Opinions with Increasing Information. The Annals of Mathematical Statistics\u00a033(3), 882\u2013886 (1962)","journal-title":"The Annals of Mathematical Statistics"},{"issue":"1","key":"32_CR3","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1006\/jeth.1999.2630","volume":"92","author":"R. Casadesus-Masanell","year":"2000","unstructured":"Casadesus-Masanell, R., Klibanoff, P., Ozdenoren, E.: Maxmin Expected Utility over Savage Acts with a Set of Priors. Journal of Economic Theory\u00a092(1), 35\u201365 (2000)","journal-title":"Journal of Economic Theory"},{"key":"32_CR4","unstructured":"deFinetti, B.: La pr\u00e9vision: Ses lois logiques, ses sources subjectives. In: Annales de l\u2019Institut Henri Poincar\u00e9 7, Paris, pp. 1\u201368 (1937)"},{"issue":"2","key":"32_CR5","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/0304-4068(89)90018-9","volume":"18","author":"I. Gilboa","year":"1989","unstructured":"Gilboa, I., Schmeidler, D.: Maxmin expected utility with non-unique prior. Journal of Mathematical Economics\u00a018(2), 141\u2013153 (1989)","journal-title":"Journal of Mathematical Economics"},{"key":"32_CR6","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":"32_CR7","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":"32_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/978-3-642-24412-4_29","volume-title":"Algorithmic Learning Theory","author":"T. Lattimore","year":"2011","unstructured":"Lattimore, T., Hutter, M.: Asymptotically Optimal Agents. In: Kivinen, J., Szepesv\u00e1ri, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol.\u00a06925, pp. 368\u2013382. Springer, Heidelberg (2011)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., Vitany, P.: An Introduction to Kolmogov Complexity and Its Applications. Springer (1993)","DOI":"10.1007\/978-1-4757-3860-5"},{"issue":"1","key":"32_CR10","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.tcs.2009.09.017","volume":"411","author":"M. M\u00fcller","year":"2010","unstructured":"M\u00fcller, M.: Stationary algorithmic probability. Theor. Comput. Sci.\u00a0411(1), 113\u2013130 (2010)","journal-title":"Theor. Comput. Sci."},{"key":"32_CR11","unstructured":"Neumann, J., Morgenstern, O.: Theory of Games and Economic Behavior. Princeton University Press (1944)"},{"key":"32_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-642-16108-7_28","volume-title":"Algorithmic Learning Theory","author":"L. Orseau","year":"2010","unstructured":"Orseau, L.: Optimality Issues of Universal Greedy Agents with Static Priors. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds.) ALT 2010. LNCS, vol.\u00a06331, pp. 345\u2013359. Springer, Heidelberg (2010)"},{"key":"32_CR13","unstructured":"Ramsey, F.: Truth and probability. In: Braithwaite, R.B. (ed.) The Foundations of Mathematics and other Logical Essays, ch. 7, pp. 156\u2013198. Brace & Co. (1931)"},{"key":"32_CR14","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":"32_CR15","volume-title":"The Foundations of Statistics","author":"L. Savage","year":"1954","unstructured":"Savage, L.: The Foundations of Statistics. Wiley, New York (1954)"},{"key":"32_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1007\/978-3-642-24412-4_27","volume-title":"Algorithmic Learning Theory","author":"P. Sunehag","year":"2011","unstructured":"Sunehag, P., Hutter, M.: Axioms for Rational Reinforcement Learning. In: Kivinen, J., Szepesv\u00e1ri, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol.\u00a06925, pp. 338\u2013352. Springer, Heidelberg (2011)"},{"key":"32_CR17","unstructured":"Sunehag, P., Hutter, M.: Principles of Solomonoff induction and AIXI. In: Solomonoff Memorial Conference, Melbourne, Australia (2011)"},{"key":"32_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-35101-3_2","volume-title":"AI 2012: Advances in Artificial Intelligence","author":"P. Sunehag","year":"2012","unstructured":"Sunehag, P., Hutter, M.: Optimistic Agents Are Asymptotically Optimal. In: Thielscher, M., Zhang, D. (eds.) AI 2012. LNCS, vol.\u00a07691, pp. 15\u201326. Springer, Heidelberg (2012)"},{"key":"32_CR19","first-page":"2413","volume":"10","author":"A.L. Strehl","year":"2009","unstructured":"Strehl, A.L., Li, L., Littman, M.L.: Reinforcement learning in finite MDPs: PAC analysis. Journal of Machine Learing Research\u00a010, 2413\u20132444 (2009)","journal-title":"Journal of Machine Learing Research"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Walley, P.: Towards a unified theory of imprecise probability. Int. J. Approx. Reasoning, 125\u2013148 (2000)","DOI":"10.1016\/S0888-613X(00)00031-1"}],"container-title":["Lecture Notes in Computer Science","Artificial General Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35506-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T15:35:48Z","timestamp":1557416148000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35506-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642355059","9783642355066"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35506-6_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}