{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:35:17Z","timestamp":1761896117637,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319231136"},{"type":"electronic","value":"9783319231143"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23114-3_9","type":"book-chapter","created":{"date-parts":[[2015,8,27]],"date-time":"2015-08-27T09:01:33Z","timestamp":1440666093000},"page":"139-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reducing the Number of Queries in Interactive Value Iteration"],"prefix":"10.1007","author":[{"given":"Hugo","family":"Gilbert","sequence":"first","affiliation":[]},{"given":"Olivier","family":"Spanjaard","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Viappiani","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Weng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,8,28]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of Twenty-First International Conference on Machine Learning, ICML 2004. ACM, New York (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"9_CR2","unstructured":"Bagnell, J., Ng, A., Schneider, J.: Solving uncertain markov decision processes. Technical report, CMU (2001)"},{"key":"9_CR3","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/TITB.2006.864480","volume":"10","author":"J Boger","year":"2006","unstructured":"Boger, J., Hoey, J., Poupart, P., Boutilier, C., Fernie, G., Mihailidis, A.: A planning system based on markov decision processes to guide people with dementia through activities of daily living. IEEE Trans. Inf. Technol. Biomed. 10, 323\u2013333 (2006)","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"9_CR4","unstructured":"Boutilier, C., Das, R., Kephart, J.O., Tesauro, G., Walsh, W.E.: Cooperative negotiation in autonomic systems using incremental utility elicitation. In: Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence, pp. 89\u201397 (2003)"},{"key":"9_CR5","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1080\/00031305.1992.10475878","volume":"46","author":"G Casella","year":"1992","unstructured":"Casella, G., George, E.I.: Explaining the gibbs sampler. Am. Stat. 46, 167\u2013174 (1992)","journal-title":"Am. Stat."},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Delage, E., Mannor, S.: Percentile optimization in uncertain Markov decision processes with application to efficient exploration. In: ICML, pp. 225\u2013232 (2007)","DOI":"10.1145\/1273496.1273525"},{"issue":"1\u20132","key":"9_CR7","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S0004-3702(00)00047-3","volume":"122","author":"R Givan","year":"2000","unstructured":"Givan, R., Leach, S., Dean, T.: Bounded-parameter Markov decision process. Artif. Intell. 122(1\u20132), 71\u2013109 (2000)","journal-title":"Artif. Intell."},{"key":"9_CR8","unstructured":"Piot, B., Geist, M., Pietquin, O.: Boosted and reward-regularized classification for apprenticeship learning. In: International conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2014, Paris, France, 5\u20139 May 2014, pp. 1249\u20131256 (2014)"},{"key":"9_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M Puterman","year":"1994","unstructured":"Puterman, M.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. Wiley, New York (1994)","edition":"1"},{"key":"9_CR10","unstructured":"Regan, K., Boutilier, C.: Regret-based reward elicitation for Markov decision Processes. In: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2009, pp. 444\u2013451. AUAI Press, Arlington (2009)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Regan, K., Boutilier, C.: Robust policy computation in reward-uncertain MDPS using nondominated policies. In: Fox, M., Poole, D. (eds.) AAAI. AAAI Press (2010)","DOI":"10.1609\/aaai.v24i1.7740"},{"key":"9_CR12","unstructured":"Regan, K., Boutilier, C.: Eliciting additive reward functions for Markov decision processes. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI 2011, vol. 3, pp. 2159\u20132164. AAAI Press (2011)"},{"key":"9_CR13","unstructured":"Regan, K., Boutilier, C.: Robust online optimization of reward-uncertain MDPs. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI 2011, vol. 3, pp. 2165\u20132171. AAAI Press (2011)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Rosenthal, S., Veloso, M.M.: Monte carlo preference elicitation for learning additive reward functions. In: RO-MAN, pp. 886\u2013891. IEEE (2012)","DOI":"10.1109\/ROMAN.2012.6343863"},{"key":"9_CR15","unstructured":"Thomaz, A., Hoffman, G., Breazeal, C.: Real-time interactive reinforcement learning for robots. In: AAAI Workshop Human Comprehensible Machine Learning, pp. 9\u201313 (2005)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Weng, P.: Markov decision processes with ordinal rewards: reference point-based preferences. In: Proceedings of the 21st International Conference on Automated Planning and Scheduling, ICAPS 2011, Freiburg, Germany, 11\u201316 June 2011 (2011)","DOI":"10.1609\/icaps.v21i1.13448"},{"key":"9_CR17","unstructured":"Weng, P.: Ordinal decision models for Markov decision processes. In: ECAI 2012\u201320th European Conference on Artificial Intelligence. Including Prestigious Applications of Artificial Intelligence (PAIS 2012) System Demonstrations Track, pp. 828\u2013833, Montpellier, France, 27\u201331 August 2012 (2012)"},{"key":"9_CR18","unstructured":"Weng, P., Zanuttini, B.: Interactive value iteration for Markov decision processes with unknown rewards. In: Rossi, F. (ed.) IJCAI. IJCAI\/AAAI (2013)"},{"issue":"2","key":"9_CR19","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1016\/0022-247X(82)90122-6","volume":"89","author":"DJ White","year":"1982","unstructured":"White, D.J.: Multi-objective infinite-horizon discounted Markov decision processes. J. Math. Anal. Appl. 89(2), 639\u2013647 (1982)","journal-title":"J. Math. Anal. Appl."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Xu, H., Mannor, S.: Parametric regret in uncertain Markov decision processes. In: CDC, pp. 3606\u20133613. IEEE (2009)","DOI":"10.1109\/CDC.2009.5400796"}],"container-title":["Lecture Notes in Computer Science","Algorithmic Decision Theory"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23114-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T19:29:39Z","timestamp":1718047779000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-23114-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319231136","9783319231143"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23114-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"28 August 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}