{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T18:06:42Z","timestamp":1725732402544},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387081"},{"type":"electronic","value":"9783642387098"}],"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\/978-3-642-40988-2_11","type":"book-chapter","created":{"date-parts":[[2013,8,28]],"date-time":"2013-08-28T10:56:40Z","timestamp":1377687400000},"page":"162-177","source":"Crossref","is-referenced-by-count":0,"title":["Iterative Model Refinement of Recommender MDPs Based on Expert Feedback"],"prefix":"10.1007","author":[{"given":"Omar Zia","family":"Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Poupart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John Mark","family":"Agosta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Twenty-First International Conference on Machine Learning, ICML (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Exploration and apprenticeship learning in reinforcement learning. In: Twenty Second International Conference on Machine Learning, ICML (2005)","DOI":"10.1145\/1015330.1015430"},{"key":"11_CR3","unstructured":"Agosta, J.M., Khan, O.Z., Poupart, P.: Evaluation results for a query-based diagnostics application. In: Fifth Workshop on Probabilistic Graphical Models, PGM (2010)"},{"key":"11_CR4","unstructured":"Altman, E.: Constrained Markov Decision Processes. CRC Press (1999)"},{"key":"11_CR5","series-title":"STAR","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-3-642-17452-0_11","volume-title":"Algorithmic Foundations of Robotics IX","author":"H. Bai","year":"2010","unstructured":"Bai, H., Hsu, D., Lee, W.S., Ngo, V.A.: Monte carlo value iteration for continuous-state POMDPs. In: Hsu, D., Isler, V., Latombe, J.-C., Lin, M.C. (eds.) Algorithmic Foundations of Robotics IX. STAR, vol.\u00a068, pp. 175\u2013191. Springer, Heidelberg (2010)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"de Campos, C.P., Ji, Q.: Improving Bayesian network parameter learning using constraints. In: International Conference in Pattern Recognition, ICPR (2008)","DOI":"10.1109\/ICPR.2008.4761287"},{"key":"11_CR7","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/11871842_63","volume-title":"Machine Learning: ECML 2006","author":"P. Geibel","year":"2006","unstructured":"Geibel, P.: Reinforcement learning for MDPs with constraints. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol.\u00a04212, pp. 646\u2013653. Springer, Heidelberg (2006)"},{"key":"11_CR8","unstructured":"Khan, O.Z., Poupart, P., Agosta, J.M.: Automated refinement of Bayes networks\u2019 parameters based on test ordering constraints. In: Neural Information Processing Systems, NIPS (2011)"},{"key":"11_CR9","unstructured":"Ng, A.Y., Russell, S.J.: Algorithms for inverse reinforcement learning. In: Seventeenth International Conference on Machine Learning, ICML (2000)"},{"key":"11_CR10","first-page":"1357","volume":"7","author":"R.S. Niculescu","year":"2006","unstructured":"Niculescu, R.S., Mitchell, T.M., Rao, R.B.: Bayesian network learning with parameter constraints. Journal of Machine Learning Research (JMLR)\u00a07, 1357\u20131383 (2006)","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"11_CR11","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1613\/jair.898","volume":"19","author":"B. Price","year":"2003","unstructured":"Price, B., Boutilier, C.: Accelerating reinforcement learning through implicit imitation. Journal of Artificial Intelligence Research (JAIR)\u00a019, 569\u2013629 (2003)","journal-title":"Journal of Artificial Intelligence Research (JAIR)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Andrew (Drew) Bagnell, J., Zinkevich, M.: Maximum margin planning. In: Twenty Third International Conference on Machine Learning, ICML (2006)","DOI":"10.1145\/1143844.1143936"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Regan, K., Boutilier, C.: Robust policy computation in reward-uncertain MDPs using nondominated policies. In: Twenty-Fourth Conference on Artificial Intelligence, AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7740"},{"key":"11_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-012-9200-2","volume":"27","author":"G. Shani","year":"2013","unstructured":"Shani, G., Pineau, J., Kaplow, R.: A survey of point-based POMDP solvers. Autonomous Agents and Multi-Agent Systems\u00a027, 1\u201351 (2013)","journal-title":"Autonomous Agents and Multi-Agent Systems"}],"container-title":["Lecture Notes in Computer Science","Advanced Information Systems Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40988-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T04:35:43Z","timestamp":1688445343000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40988-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387081","9783642387098"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40988-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}