{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:50:41Z","timestamp":1725490241024},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540735793"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-73580-9_22","type":"book-chapter","created":{"date-parts":[[2007,8,23]],"date-time":"2007-08-23T01:52:00Z","timestamp":1187833920000},"page":"273-284","source":"Crossref","is-referenced-by-count":11,"title":["Active Learning of Dynamic Bayesian Networks in Markov Decision Processes"],"prefix":"10.1007","author":[{"given":"Anders","family":"Jonsson","sequence":"first","affiliation":[]},{"given":"Andrew","family":"Barto","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"3","key":"22_CR1","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1111\/j.1467-8640.1989.tb00324.x","volume":"5","author":"T. Dean","year":"1989","unstructured":"Dean, T., Kanazawa, K.: A model for reasoning about persistence and causation. Computational Intelligence\u00a05(3), 142\u2013150 (1989)","journal-title":"Computational Intelligence"},{"key":"22_CR2","unstructured":"Boutilier, C., Dearden, R., Goldszmidt, M.: Exploiting structure in policy construction. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol. 14, pp. 1104\u20131113 (1995)"},{"key":"22_CR3","unstructured":"Feng, Z., Hansen, E., Zilberstein, Z.: Symbolic Generalization for On-line Planning. In: Proceedings of Uncertainty in Artificial Intelligence, vol. 19, pp. 209\u2013216 (2003)"},{"key":"22_CR4","unstructured":"Guestrin, C., Koller, D., Parr, R.: Max-norm Projections for Factored MDPs. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol. 17, pp. 673\u2013680 (2001)"},{"key":"22_CR5","first-page":"2259","volume":"7","author":"A. Jonsson","year":"2006","unstructured":"Jonsson, A., Barto, A.: Causal Graph Based Decomposition of Factored MDPs. Journal of Machine Learning Research\u00a07, 2259\u20132301 (2006)","journal-title":"Journal of Machine Learning Research"},{"key":"22_CR6","unstructured":"Kearns, M., Koller, D.: Efficient Reinforcement Learning in Factored MDPs. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol. 16, pp. 740\u2013747 (1999)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Buntime, W.: Theory refinement on Bayesian networks. In: Proceedings of Uncertainty in Artificial Intelligence, vol. 7, pp. 52\u201360 (1991)","DOI":"10.1016\/B978-1-55860-203-8.50010-3"},{"key":"22_CR8","unstructured":"Friedman, N., Murphy, K., Russell, S.: Learning the structure of dynamic probabilistic networks. In: Proceedings of Uncertainty in Artificial Intelligence, vol. 14, pp. 139\u2013147 (1998)"},{"key":"22_CR9","first-page":"197","volume":"20","author":"D. Heckerman","year":"1995","unstructured":"Heckerman, D., Geiger, D., Chickering, D.: Learning Bayesian networks: The combination of knowledge and statistical data. Machine Learning\u00a020, 197\u2013243 (1995)","journal-title":"Machine Learning"},{"key":"22_CR10","unstructured":"Murphy, K.: Active learning of causal Bayes net structure. Technical report, Computer Science Division, University of Berkeley (2001)"},{"key":"22_CR11","unstructured":"Steck, H., Jaakkola, T.: Unsupervised active learning in large domains. In: Proceedings of Uncertainty in Artificial Intelligence, vol. 18, pp. 469\u2013476 (2002)"},{"key":"22_CR12","unstructured":"Tong, S., Koller, D.: Active learning for structure in Bayesian networks. In: Proceedings of the International Joint Conference on Artificial Intelligence, vol. 17, pp. 863\u2013869 (2001)"},{"key":"22_CR13","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G. Schwartz","year":"1978","unstructured":"Schwartz, G.: Estimating the dimension of a model. Annals of Statistics\u00a06, 461\u2013464 (1978)","journal-title":"Annals of Statistics"},{"key":"22_CR14","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1126\/science.247.4945.978","volume":"247","author":"T. Poggio","year":"1990","unstructured":"Poggio, T., Girosi, F.: Regularization Algorithms for Learning that are Equivalent to Multilayer Networks. Science\u00a0247, 978\u2013982 (1990)","journal-title":"Science"},{"key":"22_CR15","volume-title":"Reinforcement Learning: An Introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"22_CR16","unstructured":"Chickering, D., Geiger, D., Heckerman, D.: Learning Bayesian networks: search methods and experimental results. In: Proceedings of Artificial Intelligence and Statistics, vol. 5, pp. 112\u2013128 (1995)"},{"key":"22_CR17","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T. Dietterich","year":"2000","unstructured":"Dietterich, T.: Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research\u00a013, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"22_CR18","unstructured":"Ghavamzadeh, M., Mahadevan, S.: Continuous-Time Hierarchical Reinforcement Learning. In: Proceedings of the International Conference on Machine Learning, vol. 18, pp. 186\u2013193 (2001)"}],"container-title":["Lecture Notes in Computer Science","Abstraction, Reformulation, and Approximation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-73580-9_22.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T05:52:24Z","timestamp":1619502744000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-73580-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540735793"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-73580-9_22","relation":{},"subject":[]}}