{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T20:26:49Z","timestamp":1649017609821},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,5,1]],"date-time":"2011-05-01T00:00:00Z","timestamp":1304208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2012,2]]},"DOI":"10.1007\/s10462-011-9224-z","type":"journal-article","created":{"date-parts":[[2011,4,30]],"date-time":"2011-04-30T02:23:53Z","timestamp":1304130233000},"page":"157-167","source":"Crossref","is-referenced-by-count":5,"title":["New prioritized value iteration for Markov decision processes"],"prefix":"10.1007","volume":"37","author":[{"given":"Ma. de Guadalupe","family":"Garcia-Hernandez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Ruiz-Pinales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eva","family":"Onaindia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. Gabriel","family":"Avi\u00f1a-Cervantes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Ledesma-Orozco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edgar","family":"Alvarado-Mendez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto","family":"Reyes-Ballesteros","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,5,1]]},"reference":[{"key":"9224_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal S, Roth D (2002) Learning a sparse representation for object detection. In: Proceedings of the 7th European conference on computer vision. Copenhagen, Denmark, pp 1\u201315","DOI":"10.1007\/3-540-47979-1_8"},{"key":"9224_CR2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1090\/S0002-9904-1954-09848-8","volume":"60","author":"RE Bellman","year":"1954","unstructured":"Bellman RE (1954) The theory of dynamic programming. Bull Amer Math Soc 60: 503\u2013516","journal-title":"Bull Amer Math Soc"},{"key":"9224_CR3","volume-title":"Dynamic programming","author":"RE Bellman","year":"1957","unstructured":"Bellman RE (1957) Dynamic programming. Princeton University Press, New Jersey"},{"key":"9224_CR4","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas DP (1995) Dynamic programming and optimal control. Athena Scientific, Massachusetts"},{"key":"9224_CR5","unstructured":"Bhuma K, Goldsmith J (2003) Bidirectional LAO* algorithm. In: Proceedings of indian international conferences on artificial intelligence. p 980\u2013992"},{"key":"9224_CR6","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1214\/aoms\/1177700285","volume":"36","author":"D Blackwell","year":"1965","unstructured":"Blackwell D (1965) Discounted dynamic programming. Ann Math Stat 36: 226\u2013235","journal-title":"Ann Math Stat"},{"key":"9224_CR7","unstructured":"Bonet B, Geffner H (2003a) Faster heuristic search algorithms for planning with uncertainty and full feedback. In: Proceedings of the 18th international joint conference on artificial intelligence. Morgan Kaufmann, Acapulco, M\u00e9xico, pp 1233\u20131238"},{"key":"9224_CR8","unstructured":"Bonet B, Geffner H (2003b) Labeled RTDP: improving the convergence of real-time dynamic programming. In: Proceedings of the international conference on automated planning and scheduling. Trento, Italy, pp 12\u201321"},{"key":"9224_CR9","unstructured":"Bonet B, Geffner H (2006) Learning depth-first search: a unified approach to heuristic search in deterministic and non-deterministic settings and its application to MDP. In: Proceedings of the 16th international conference on automated planning and scheduling. Cumbria, UK"},{"key":"9224_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.575","volume":"11","author":"C Boutilier","year":"1999","unstructured":"Boutilier C, Dean T, Hanks S (1999) Decision-theoretic planning: structural assumptions and computational leverage. J Artif Intell Res 11: 1\u201394","journal-title":"J Artif Intell Res"},{"key":"9224_CR11","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84628-690-2","volume-title":"Simulation-based algorithms for Markov decision processes Communications and control engineering","author":"I Chang","year":"2007","unstructured":"Chang I, Soo H (2007) Simulation-based algorithms for Markov decision processes Communications and control engineering. Springer, London"},{"key":"9224_CR12","unstructured":"Dai P, Goldsmith J (2007a) Faster dynamic programming for Markov decision processes. Technical report. Doctoral consortium, department of computer science and engineering. University of Washington"},{"key":"9224_CR13","unstructured":"Dai P, Goldsmith J (2007b) Topological value iteration algorithm for Markov decision processes. In: Proceedings of the 20th international joint conference on artificial intelligence. Hyderabad, India, pp 1860\u20131865"},{"key":"9224_CR14","unstructured":"Dai P, Hansen EA (2007c) Prioritizing bellman backups without a priority queue. In: Proceedings of the 17th international conference on automated planning and scheduling, association for the advancement of artificial intelligence. Rhode Island, USA, pp 113\u2013119"},{"key":"9224_CR15","unstructured":"Dibangoye JS, Chaib-draa B, Mouaddib A (2008) A Novel prioritization technique for solving Markov decision processes. In: Proceedings of the 21st international FLAIRS (The Florida Artificial Intelligence Research Society) conference, association for the advancement of artificial intelligence. Florida, USA"},{"key":"9224_CR16","doi-asserted-by":"crossref","unstructured":"Ferguson D, Stentz A (2004) Focused propagation of MDPs for path planning. In: Proceedings of the 16th IEEE international conference on tools with artificial intelligence. pp 310\u2013317","DOI":"10.1109\/ICTAI.2004.64"},{"key":"9224_CR17","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/S0004-3702(01)00106-0","volume":"129","author":"EA Hansen","year":"2001","unstructured":"Hansen EA, Zilberstein S (2001) LAO: a heuristic search algorithm that finds solutions with loops. Artif Intell 129: 35\u201362","journal-title":"Artif Intell"},{"key":"9224_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s001860200252","volume":"57","author":"K Hinderer","year":"2003","unstructured":"Hinderer K, Waldmann KH (2003) The critical discount factor for finite Markovian decision processes with an absorbing set. Math Methods Oper Res 57: 1\u201319","journal-title":"Math Methods Oper Res"},{"key":"9224_CR19","unstructured":"Li L (2009) A unifying framework for computational reinforcement learning theory. PhD Thesis. The state university of New Jersey, New Brunswick. NJ"},{"key":"9224_CR20","unstructured":"Littman ML, Dean TL, Kaelbling LP (1995) On the complexity of solving Markov decision problems.In: Proceedings of the 11th international conference on uncertainty in artificial intelligence. Montreal, Quebec pp 394\u2013402"},{"key":"9224_CR21","unstructured":"McMahan HB, Gordon G (2005a) Fast exact planning in Markov decision processes. In: Proceedings of the 15th international conference on automated planning and scheduling. Monterey, CA, USA"},{"key":"9224_CR22","unstructured":"McMahan HB, Gordon G (2005b) Generalizing Dijkstra\u2019s algorithm and gaussian elimination for solving MDPs. Technical report, Carnegie Mellon University, Pittsburgh"},{"key":"9224_CR23","unstructured":"Meuleau N, Brafman R, Benazera E (2006) Stochastic over-subscription planning using hierarchies of MDPs. In: Proceedings of the 16th international conference on automated planning and scheduling. Cumbria, UK, pp 121\u2013130"},{"key":"9224_CR24","first-page":"103","volume":"13","author":"A Moore","year":"1993","unstructured":"Moore A, Atkeson C (1993) Prioritized sweeping: reinforcement learning with less data and less real time. Mach Learn 13: 103\u2013130","journal-title":"Mach Learn"},{"key":"9224_CR25","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes","author":"ML Puterman","year":"1994","unstructured":"Puterman ML (1994) Markov decision processes. Wiley Editors, New York"},{"key":"9224_CR26","volume-title":"Markov decision processes","author":"ML Puterman","year":"2005","unstructured":"Puterman ML (2005) Markov decision processes. Wiley Inter Science Editors, New York"},{"key":"9224_CR27","volume-title":"Artificial intelligence: a modern approach. Making complex decisions (Ch-17)","author":"S Russell","year":"2005","unstructured":"Russell S (2005) Artificial intelligence: a modern approach. Making complex decisions (Ch-17), 2nd edn. Pearson Prentice Hill Ed., USA","edition":"2"},{"issue":"6","key":"9224_CR28","doi-asserted-by":"crossref","first-page":"1592","DOI":"10.1109\/TSMCB.2008.928222","volume":"38","author":"G Shani","year":"2008","unstructured":"Shani G, Brafman R, Shimony S (2008) Prioritizing point-based POMDP solvers. IEEE Trans Syst Man Cybern 38(6): 1592\u20131605","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"9224_CR29","first-page":"599","volume":"35","author":"M Sniedovich","year":"2006","unstructured":"Sniedovich M (2006) Dijkstra\u2019s algorithm revisited: the dynamic programming connexion. Control Cybern 35: 599\u2013620","journal-title":"Control Cybern"},{"key":"9224_CR30","doi-asserted-by":"crossref","DOI":"10.1201\/EBK0824740993","volume-title":"Dynamic programming: foundations and principles","author":"M Sniedovich","year":"2010","unstructured":"Sniedovich M (2010) Dynamic programming: foundations and principles, 2nd edn. Pure and Applied Mathematics Series, UK","edition":"2"},{"key":"9224_CR31","doi-asserted-by":"crossref","DOI":"10.1002\/047001363X","volume-title":"A first course in stochastic models. Discrete-time Markov decision processes (Ch-6)","author":"HC Tijms","year":"2003","unstructured":"Tijms HC (2003) A first course in stochastic models. Discrete-time Markov decision processes (Ch-6). Wiley Editors, UK"},{"key":"9224_CR32","unstructured":"Vanderbei RJ (1996) Optimal sailing strategies. Statistics and operations research program, University of Princeton, USA ( http:\/\/www.orfe.princeton.edu\/~rvdb\/sail\/sail.html )"},{"key":"9224_CR33","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-74388-2","volume-title":"Linear programming: foundations and extensions","author":"RJ Vanderbei","year":"2008","unstructured":"Vanderbei RJ (2008) Linear programming: foundations and extensions, 3rd edn. Springer, New York","edition":"3"},{"key":"9224_CR34","first-page":"851","volume":"6","author":"D Wingate","year":"2005","unstructured":"Wingate D, Seppi KD (2005) Prioritization methods for accelerating MDP solvers. J Mach Learn Res 6: 851\u2013881","journal-title":"J Mach Learn Res"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-011-9224-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-011-9224-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-011-9224-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T11:35:12Z","timestamp":1560166512000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-011-9224-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,5,1]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,2]]}},"alternative-id":["9224"],"URL":"https:\/\/doi.org\/10.1007\/s10462-011-9224-z","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,5,1]]}}}