{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:30:54Z","timestamp":1725474654186},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540499947"},{"type":"electronic","value":"9783540499954"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11944836_23","type":"book-chapter","created":{"date-parts":[[2006,11,27]],"date-time":"2006-11-27T23:48:02Z","timestamp":1164671282000},"page":"236-247","source":"Crossref","is-referenced-by-count":3,"title":["Testing Probabilistic Equivalence Through Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Jos\u00e9e","family":"Desharnais","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois","family":"Laviolette","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sami","family":"Zhioua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Blute, R., Desharnais, J., Edalat, A., Panangaden, P.: Bisimulation for labelled Markov processes. In: Proc. of the Twelfth IEEE Symposium On Logic In Computer Science, Warsaw, Poland (1997)","DOI":"10.1109\/LICS.1997.614943"},{"key":"23_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/3-540-45465-9_46","volume-title":"Automata, Languages and Programming","author":"F. Breugel van","year":"2002","unstructured":"van Breugel, F., Shalit, S., Worrell, J.B.: Testing labelled markov processes. In: Widmayer, P., Triguero, F., Morales, R., Hennessy, M., Eidenbenz, S., Conejo, R. (eds.) ICALP 2002. LNCS, vol.\u00a02380, pp. 537\u2013548. Springer, Heidelberg (2002)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Van Breugel, F., Worrell, J.: Approximating and computing behavioural distances in probabilistic transition systems. Theoretical Computer Science (2006)","DOI":"10.1016\/j.tcs.2006.05.021"},{"key":"23_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611","volume-title":"Elements of Information Theory","author":"T.M. Cover","year":"1991","unstructured":"Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, Chichester (1991)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Desharnais, J., Laviolette, F., Darsini Moturu, K., Zhioua, S.: Trace equivalence characterization through reinforcement learning. In: 19th Canadian Conference on Artificial Intelligence (2006) (accepted for publication)","DOI":"10.1007\/11766247_32"},{"key":"23_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/3-540-44581-1_39","volume-title":"Computational Learning Theory","author":"E. Even-Dar","year":"2001","unstructured":"Even-Dar, E., Mansour, Y.: Learning rates for Q-learning. In: Helmbold, D.P., Williamson, B. (eds.) COLT 2001 and EuroCOLT 2001. LNCS, vol.\u00a02111, pp. 589\u2013604. Springer, Heidelberg (2001)"},{"key":"23_CR7","unstructured":"Fiechter, C.N.: Design and Analysis of Efficient Reinforcement Learning Algorithms. PhD thesis, Univ. of Pittsburgh (1997)"},{"key":"23_CR8","unstructured":"Giacalone, A., Jou, C., Smolka, S.: Algebraic reasoning for probabilistic concurrent systems. In: Proceedings of the Working Conference on Programming Concepts and Methods. IFIP TC2 (1990)"},{"key":"23_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/3-540-57208-2_6","volume-title":"CONCUR\u201993","author":"R.J. Glabbeek Van","year":"1993","unstructured":"Van Glabbeek, R.J.: The linear time - branching time spectrum ii. In: Best, E. (ed.) CONCUR 1993. LNCS, vol.\u00a0715, pp. 66\u201381. Springer, Heidelberg (1993)"},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science","volume-title":"CONCUR \u201990","author":"C.-C. Jou","year":"1990","unstructured":"Jou, C.-C., Smolka, S.A.: Equivalences, congruences, and complete axiomatizations for probabilistic processes. In: Baeten, J.C.M., Klop, J.W. (eds.) CONCUR 1990. LNCS, vol.\u00a0458. Springer, Heidelberg (1990)"},{"key":"23_CR11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.P.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"23_CR12","first-page":"996","volume-title":"Proc. of the 1998 conference on Advances in neural information processing systems II","author":"M. Kearns","year":"1999","unstructured":"Kearns, M., Singh, S.: Finite-sample convergence rates for q-learning and indirect algorithms. In: Proc. of the 1998 conference on Advances in neural information processing systems II, pp. 996\u20131002. MIT Press, Cambridge (1999)"},{"issue":"1","key":"23_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0890-5401(91)90030-6","volume":"94","author":"K.G. Larsen","year":"1991","unstructured":"Larsen, K.G., Skou, A.: Bisimulation through probabilistic testing. Inf. Comput.\u00a094(1), 1\u201328 (1991)","journal-title":"Inf. Comput."},{"key":"23_CR14","unstructured":"Lowe, G.: Representing Nondeterministic and Probabilistic Behaviour in Reactive Processes. Technical report, Progr. Res. Group, Oxford University (1993)"},{"key":"23_CR15","volume-title":"Introduction to Reinforcement Learning","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"23_CR16","unstructured":"Watkins, C.: Learning from Delayed Rewards. PhD thesis, Univ. of Cambridge (1989)"},{"key":"23_CR17","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","FSTTCS 2006: Foundations of Software Technology and Theoretical Computer Science"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11944836_23.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T03:17:44Z","timestamp":1619493464000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11944836_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540499947","9783540499954"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/11944836_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}