{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T23:05:18Z","timestamp":1725750318127},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642409349"},{"type":"electronic","value":"9783642409356"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40935-6_25","type":"book-chapter","created":{"date-parts":[[2013,9,27]],"date-time":"2013-09-27T05:14:50Z","timestamp":1380258890000},"page":"354-366","source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised Model-Free Representation Learning"],"prefix":"10.1007","author":[{"given":"Daniil","family":"Ryabko","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"25_CR1","doi-asserted-by":"crossref","first-page":"041925","DOI":"10.1103\/PhysRevE.79.041925","volume":"79","author":"F. Creutzig","year":"2009","unstructured":"Creutzig, F., Globerson, A., Tishby, N.: Past-future information bottleneck in dynamical systems. Phys. Rev. E 79, 041925 (2009)","journal-title":"Phys. Rev. E"},{"key":"25_CR2","unstructured":"Ferns, N., Castro, P.S., Precup, D., Panangaden, P.: Methods for computing state similarity in markov decision processes. In: Proceedings of UAI (2006)"},{"issue":"1","key":"25_CR3","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/S0004-3702(02)00376-4","volume":"147","author":"R. Givan","year":"2003","unstructured":"Givan, R., Dean, T., Greig, M.: Equivalence notions and model minimization in markov decision processes. Artificial Intelligence\u00a0147(1), 163\u2013223 (2003)","journal-title":"Artificial Intelligence"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Gray, R.: Entropy and information theory. Springer (1990)","DOI":"10.1007\/978-1-4757-3982-4"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Lerma, O., Lasserre, J.B.: Markov chains and invariant probabilities. Birkh\u00e4user (2003)","DOI":"10.1007\/978-3-0348-8024-4"},{"key":"25_CR6","doi-asserted-by":"crossref","first-page":"3","DOI":"10.2478\/v10229-011-0002-8","volume":"1","author":"M. Hutter","year":"2009","unstructured":"Hutter, M.: Feature reinforcement learning: Part I. Unstructured MDPs. Journal of General Artificial Intelligence\u00a01, 3\u201324 (2009)","journal-title":"Journal of General Artificial Intelligence"},{"key":"25_CR7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1016\/S0167-7152(02)00124-4","volume":"58","author":"R.L. Karandikar","year":"2002","unstructured":"Karandikar, R.L., Vidyasagar, M.: Rates of uniform convergence of empirical means with mixing processes. Statistics and Probability Letters\u00a058, 297\u2013307 (2002)","journal-title":"Statistics and Probability Letters"},{"key":"25_CR8","unstructured":"Maillard, O., Munos, R., Ryabko, D.: Selecting the state-representation in reinforcement learning. In: NIPS, Granada, Spain, pp. 2627\u20132635 (2011)"},{"key":"25_CR9","unstructured":"Maillard, O., Nguyen, P., Ortner, R., Ryabko, D.: Optimal regret bounds for selecting the state representation in reinforcement learning. In: ICML, Atlanta, USA. JMLR W&CP, vol.\u00a028(1), pp. 543\u2013551 (2013)"},{"key":"25_CR10","unstructured":"Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming, vol.\u00a0414. Wiley-Interscience (2009)"},{"issue":"1","key":"25_CR11","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","volume":"3","author":"L. Rabiner","year":"1986","unstructured":"Rabiner, L., Juang, B.: An introduction to hidden Markov models. IEEE ASSP Magazine\u00a03(1), 4\u201316 (1986)","journal-title":"IEEE ASSP Magazine"},{"key":"25_CR12","unstructured":"Ravindran, B., Barto, A.G.: Relativized options: Choosing the right transformation. In: Machine Learning, Proceedings of the Twentieth International Conference, ICML 2003, Washington, DC, USA, August 21-24, vol.\u00a02, pp. 608\u2013615 (2003)"},{"key":"25_CR13","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1016\/j.stamet.2005.10.004","volume":"3","author":"B. Ryabko","year":"2006","unstructured":"Ryabko, B., Astola, J.: Universal codes as a basis for time series testing. Statistical Methodology\u00a03, 375\u2013397 (2006)","journal-title":"Statistical Methodology"},{"key":"25_CR14","first-page":"645","volume":"7","author":"D. Ryabko","year":"2006","unstructured":"Ryabko, D.: Pattern recognition for conditionally independent data. Journal of Machine Learning Research\u00a07, 645\u2013664 (2006)","journal-title":"Journal of Machine Learning Research"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Ryabko, D.: Time-series information and learning. In: Proc. 2013 IEEE International Symposium on Information Theory, Istanbul, Turkey. IEEE (2013)","DOI":"10.1109\/ISIT.2013.6620455"},{"issue":"3-4","key":"25_CR16","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1023\/A:1010388907793","volume":"104","author":"C.R. Shalizi","year":"2001","unstructured":"Shalizi, C.R., Crutchfield, J.P.: Computational mechanics: Pattern and prediction, structure and simplicity. Journal of Statistical Physics\u00a0104(3-4), 817\u2013879 (2001)","journal-title":"Journal of Statistical Physics"},{"key":"25_CR17","first-page":"142","volume":"4","author":"C.E. Shannon","year":"1959","unstructured":"Shannon, C.E.: Coding theorems for a discrete source with a fidelity criterion. IRE Nat. Conv. Rec.\u00a04, 142\u2013163 (1959)","journal-title":"IRE Nat. Conv. Rec."},{"key":"25_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1007\/978-3-642-16108-7_29","volume-title":"Algorithmic Learning Theory","author":"P. Sunehag","year":"2010","unstructured":"Sunehag, P., Hutter, M.: Consistency of feature markov processes. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds.) ALT 2010, LNCS, vol.\u00a06331, pp. 360\u2013374. Springer, Heidelberg (2010)"},{"key":"25_CR19","unstructured":"Taylor, J., Precup, D., Panangaden, P.: Bounding performance loss in approximate mdp homomorphisms. In: Advances in Neural Information Processing Systems, vol.\u00a021, pp. 1649\u20131656 (2009)"},{"key":"25_CR20","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. In: Proceedings of the 37th Annual Allerton Conference on Communication, Control, and Computing, pp. 368\u2013377 (1999)"},{"key":"25_CR21","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1214\/09-IMSCOLL508","volume":"5","author":"A. Vaart","year":"2009","unstructured":"van der Vaart, A., Wellner, J.A.: A note on bounds for VC dimensions. Institute of Mathematical Statistics Collections\u00a05, 103 (2009)","journal-title":"Institute of Mathematical Statistics Collections"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Learning Theory"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40935-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T02:02:28Z","timestamp":1558317748000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40935-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642409349","9783642409356"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40935-6_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}