Stochastic dynamic programming with factored representations

From MaRDI portal
Publication:1583230

DOI10.1016/S0004-3702(00)00033-3zbMath0948.68167WikidataQ126771357 ScholiaQ126771357MaRDI QIDQ1583230

Craig Boutilier, Moisés Goldszmidt, Richard Dearden

Publication date: 26 October 2000

Published in: Artificial Intelligence (Search for Journal in Brave)




Related Items

Learning classifier systems: a surveyComplexity results and algorithms for possibilistic influence diagramsComputational Benefits of Intermediate Rewards for Goal-Reaching Policy LearningSymmetric approximate linear programming for factored MDPs with application to constrained problemsScalable transfer learning in heterogeneous, dynamic environmentsRethinking formal models of partially observable multiagent decision makingAlgebraic decompositions of DP problems with linear dynamicsEfficient approximate linear programming for factored MDPsReal-time dynamic programming for Markov decision processes with imprecise probabilitiesDecision-theoretic planning with generalized first-order decision diagramsA framework and a mean-field algorithm for the local control of spatial processesAgent's actions as a classification criteria for the state space in a learning from rewards systemA Verified Compositional Algorithm for AI PlanningEmbedding a state space model into a Markov decision processAn integrated approach to solving influence diagrams and finite-horizon partially observable decision processesRecursive estimation of high-order Markov chains: approximation by finite mixturesA POMDP framework for coordinated guidance of autonomous UAVs for multitarget trackingAnalysis of customer lifetime value and marketing expenditure decisions through a Markovian-based modelEfficient algorithms for risk-sensitive Markov decision processes with limited budgetInfluence of modeling structure in probabilistic sequential decision problemsACTION FAILURE RECOVERY VIA MODEL-BASED DIAGNOSIS AND CONFORMANT PLANNINGA Sufficient Statistic for Influence in Structured Multiagent EnvironmentsEquivalence notions and model minimization in Markov decision processesSolving factored MDPs using non-homogeneous partitionsConstraint solving in uncertain and dynamic environments: A survey


Uses Software


Cites Work