{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:29:50Z","timestamp":1725550190478},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642116872"},{"type":"electronic","value":"9783642116889"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"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":[[2010]]},"DOI":"10.1007\/978-3-642-11688-9_3","type":"book-chapter","created":{"date-parts":[[2010,3,22]],"date-time":"2010-03-22T01:34:40Z","timestamp":1269221680000},"page":"65-84","source":"Crossref","is-referenced-by-count":2,"title":["Switching between Representations in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Harm","family":"van Seijen","sequence":"first","affiliation":[]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[]},{"given":"Leon","family":"Kester","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","first-page":"1743","volume":"7","author":"P. Abbeel","year":"2006","unstructured":"Abbeel, P., Koller, D., Ng, A.: Learning factor graphs in polynomial time and sample complexity. The Journal of Machine Learning Research\u00a07, 1743\u20131788 (2006)","journal-title":"The Journal of Machine Learning Research"},{"key":"3_CR2","first-page":"679","volume":"6","author":"R.E. Bellman","year":"1957","unstructured":"Bellman, R.E.: A Markov decision process. Journal of Mathematical Mechanics\u00a06, 679\u2013684 (1957)","journal-title":"Journal of Mathematical Mechanics"},{"key":"3_CR3","unstructured":"Boutilier, C., Dearden, R., Goldszmidt, M.: Exploiting structure in policy construction. In: International Joint Conference on Artificial Intelligence, vol.\u00a014, pp. 1104\u20131113 (1995)"},{"key":"3_CR4","volume-title":"Proceedings of the 26th Annual International Conference on Machine Learning","author":"C. Diuk","year":"2009","unstructured":"Diuk, C., Li, L., Leffler, B.: The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning. In: Proceedings of the 26th Annual International Conference on Machine Learning. ACM, New York (2009)"},{"key":"3_CR5","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1613\/jair.1000","volume":"19","author":"C. Guestrin","year":"2003","unstructured":"Guestrin, C., Koller, D., Parr, R., Venkataraman, S.: Efficient solution algorithms for factored mdps. Journal of Artificial Intelligence Research\u00a019, 399\u2013468 (2003)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"3_CR6","first-page":"279","volume-title":"Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence","author":"J. Hoey","year":"1999","unstructured":"Hoey, J., St-Aubin, R., Hu, A., Boutilier, C.: Spudd: Stochastic planning using decision diagrams. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, pp. 279\u2013288. Morgan Kaufmann, San Francisco (1999)"},{"key":"3_CR7","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":"3_CR8","unstructured":"Kearns, M., Koller, D.: Efficient reinforcement learning in factored mdps. In: International Joint Conference on Artificial Intelligence, vol.\u00a016, pp. 740\u2013747 (1999)"},{"key":"3_CR9","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1145\/1390156.1390228","volume-title":"Proceedings of the 25th international conference on Machine learning","author":"L. Li","year":"2008","unstructured":"Li, L., Littman, M., Walsh, T.: Knows what it knows: a framework for self-aware learning. In: Proceedings of the 25th international conference on Machine learning, pp. 568\u2013575. ACM, New York (2008)"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1214\/aos\/1176343541","volume":"4","author":"D. Siegmund","year":"1976","unstructured":"Siegmund, D.: Importance sampling in the monte carlo study of sequential tests. Annals of Statistics\u00a04, 673\u2013684 (1976)","journal-title":"Annals of Statistics"},{"key":"3_CR11","first-page":"1089","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"R. St-Aubin","year":"2000","unstructured":"St-Aubin, R., Hoey, J., Boutilier, C.: Apricodd: Approximate policy construction using decision diagrams. In: Proceedings of Advances in Neural Information Processing Systems, pp. 1089\u20131095. MIT Press, Cambridge (2000)"},{"key":"3_CR12","first-page":"645","volume-title":"Proceedings of the Twenty-Second National Conference on Artificial Intelligence","author":"A. Strehl","year":"2007","unstructured":"Strehl, A., Diuk, C., Littman, M.: Efficient structure learning in factored-state mdps. In: Proceedings of the Twenty-Second National Conference on Artificial Intelligence, vol.\u00a022, p. 645. AAAI Press\/MIT Press, Menlo Park\/Cambridge (2007)"},{"key":"3_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"}],"container-title":["Studies in Computational Intelligence","Interactive Collaborative Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11688-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T20:07:03Z","timestamp":1558123623000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11688-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642116872","9783642116889"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11688-9_3","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2010]]}}}