{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T22:29:14Z","timestamp":1678832954712},"reference-count":33,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[2003,7,1]],"date-time":"2003-07-01T00:00:00Z","timestamp":1057017600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2013,7,25]],"date-time":"2013-07-25T00:00:00Z","timestamp":1374710400000},"content-version":"vor","delay-in-days":3677,"URL":"https:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2003,7]]},"DOI":"10.1016\/s0004-3702(02)00377-6","type":"journal-article","created":{"date-parts":[[2003,2,17]],"date-time":"2003-02-17T17:19:30Z","timestamp":1045502370000},"page":"225-251","source":"Crossref","is-referenced-by-count":4,"title":["Solving factored MDPs using non-homogeneous partitions"],"prefix":"10.1016","volume":"147","author":[{"given":"Kee-Eung","family":"Kim","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Dean","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0004-3702(02)00377-6_BIB001","series-title":"Proceedings of the International Conference on Computer-Aided Design","article-title":"Algebraic decision diagrams and their applications","author":"Bahar","year":"1993"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB002","series-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1996"},{"issue":"6","key":"10.1016\/S0004-3702(02)00377-6_BIB003","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1109\/9.24227","article-title":"Adaptive aggregation for infinite horizon dynamic programming","volume":"34","author":"Bertsekas","year":"1989","journal-title":"IEEE Trans. Automat. Control"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB004","doi-asserted-by":"crossref","DOI":"10.1613\/jair.575","article-title":"Decision-theoretic planning: Structural assumptions and computational leverage","volume":"11","author":"Boutilier","year":"1999","journal-title":"J. Artificial Intelligence Res."},{"key":"10.1016\/S0004-3702(02)00377-6_BIB005","series-title":"Proceedings ICML-96","article-title":"Approximating value trees in structured dynamic programming","author":"Boutilier","year":"1996"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB006","series-title":"Proceedings IJCAI-95, Montreal, Quebec","first-page":"1104","article-title":"Exploiting structure in policy construction","author":"Boutilier","year":"1995"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB007","series-title":"Proceedings UAI-96","article-title":"Context-specific independence in Bayesian networks","author":"Boutilier","year":"1996"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB008","series-title":"Proceedings ICML-99","article-title":"Least-squares temporal difference learning","author":"Boyan","year":"1999"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB009","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/BF00114723","article-title":"Linear least-squares algorithms for temporal difference learning","volume":"22","author":"Bradtke","year":"1996","journal-title":"Machine Learning"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB010","series-title":"Proceedings IJCAI-91, Sydney, Australia","article-title":"Input generalization in delayed reinforcement learning: An algorithm and performance comparisons","author":"Chapman","year":"1991"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB011","series-title":"Proceedings AAAI-97, Providence, RI","article-title":"Model minimization in Markov decision processes","author":"Dean","year":"1997"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB012","series-title":"Proceedings UAI-97","article-title":"Model reduction techniques for computing approximately optimal solutions for Markov decision processes","author":"Dean","year":"1997"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB013","first-page":"143","article-title":"A model for reasoning about persistence and causation","author":"Dean","year":"1989","journal-title":"Comput. Intelligence"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB014","series-title":"Proceedings IJCAI-95, Montreal, Quebec","article-title":"The BATmobile: Towards a Bayesian automated taxi","author":"Forbes","year":"1995"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB015","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/S0004-3702(00)00047-3","article-title":"Bounded-parameter Markov decision processes","volume":"122","author":"Givan","year":"2000","journal-title":"Artificial Intelligence"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB016","series-title":"Proceedings AIPS-2000","article-title":"The complexity of model aggregation","author":"Goldsmith","year":"2000"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB017","doi-asserted-by":"crossref","unstructured":"G.J. Gordon, Stable function approximation in dynamic programming, Technical Report CMU-CS-103, School of Computer Science, Carnegie Mellon University, 1995","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB018","series-title":"Proceedings UAI-99","article-title":"SPUDD: Stochastic planning using decision diagrams","author":"Hoey","year":"1999"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB019","series-title":"Introduction to Automata Theory, Languages, and Computation","author":"Hopcroft","year":"1979"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB020","series-title":"Proceedings IJCAI-99, Stockholm, Sweden","article-title":"A sparse sampling algorithm for near-optimal planning in large Markov decision processes","author":"Kearns","year":"1999"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB021","series-title":"Proceedings NIPS-98","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","author":"Kearns","year":"1998"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB022","series-title":"Proceedings IJCAI-99, Stockholm, Sweden","article-title":"Computing factored value functions for policies in structured MDPs","author":"Koller","year":"1999"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB023","series-title":"Proceedings UAI-2000","article-title":"Policy iteration for factored MDPs","author":"Koller","year":"2000"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB024","doi-asserted-by":"crossref","DOI":"10.1613\/jair.505","article-title":"The computational complexity of probabilistic planning","volume":"9","author":"Littman","year":"1998","journal-title":"J. Artificial Intelligence Res."},{"key":"10.1016\/S0004-3702(02)00377-6_BIB025","series-title":"Proceedings AAAI-1999, Orlando, FL","article-title":"On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems","author":"Madani","year":"1999"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB026","series-title":"Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior (SAB'96)","article-title":"Learning to use selective attention and short-term memory in sequential tasks","author":"McCallum","year":"1998"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB027","series-title":"Proceedings IJCAI-99, Stockholm, Sweden","article-title":"Variable resolution discretization for high-accuracy solutions of optimal control problems","author":"Munos","year":"1999"},{"issue":"3","key":"10.1016\/S0004-3702(02)00377-6_BIB028","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1287\/moor.12.3.441","article-title":"The complexity of Markov decision processes","volume":"12","author":"Papadimitriou","year":"1987","journal-title":"Math. Oper. Res."},{"key":"10.1016\/S0004-3702(02)00377-6_BIB029","series-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"1994"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB030","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/BF00993308","article-title":"An upper bound on the loss from approximate optimal-value functions","volume":"16","author":"Singh","year":"1994","journal-title":"Machine Learning"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB031","unstructured":"F. Somenzi, CUDD: CU Decision Diagram Package Release 2.3.0, Department of Electrical and Computer Engineering, University of Colorado at Boulder, 1998"},{"key":"10.1016\/S0004-3702(02)00377-6_BIB032","series-title":"Proceedings NIPS-2000","article-title":"APRICODD: Approximate policy construction using decision diagrams","author":"St-Aubin","year":"2000"},{"issue":"4","key":"10.1016\/S0004-3702(02)00377-6_BIB033","doi-asserted-by":"crossref","DOI":"10.1287\/opre.42.4.739","article-title":"Markov decision processes with imprecise transition probabilities","volume":"42","author":"White","year":"1994","journal-title":"Oper. Res."}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370202003776?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370202003776?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T16:52:21Z","timestamp":1584463941000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370202003776"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,7]]},"references-count":33,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2003,7]]}},"alternative-id":["S0004370202003776"],"URL":"https:\/\/doi.org\/10.1016\/s0004-3702(02)00377-6","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2003,7]]}}}