Stochastic dynamic programming with factored representations

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)

zbMATH Keywords

Bayesian networksMarkov decision processesregressiondecision treesabstractiondecision-theoretic planning

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items

Learning classifier systems: a survey ⋮ Complexity results and algorithms for possibilistic influence diagrams ⋮ Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning ⋮ Symmetric approximate linear programming for factored MDPs with application to constrained problems ⋮ Scalable transfer learning in heterogeneous, dynamic environments ⋮ Rethinking formal models of partially observable multiagent decision making ⋮ Algebraic decompositions of DP problems with linear dynamics ⋮ Efficient approximate linear programming for factored MDPs ⋮ Real-time dynamic programming for Markov decision processes with imprecise probabilities ⋮ Decision-theoretic planning with generalized first-order decision diagrams ⋮ A framework and a mean-field algorithm for the local control of spatial processes ⋮ Agent's actions as a classification criteria for the state space in a learning from rewards system ⋮ A Verified Compositional Algorithm for AI Planning ⋮ Embedding a state space model into a Markov decision process ⋮ An integrated approach to solving influence diagrams and finite-horizon partially observable decision processes ⋮ Recursive estimation of high-order Markov chains: approximation by finite mixtures ⋮ A POMDP framework for coordinated guidance of autonomous UAVs for multitarget tracking ⋮ Analysis of customer lifetime value and marketing expenditure decisions through a Markovian-based model ⋮ Efficient algorithms for risk-sensitive Markov decision processes with limited budget ⋮ Influence of modeling structure in probabilistic sequential decision problems ⋮ ACTION FAILURE RECOVERY VIA MODEL-BASED DIAGNOSIS AND CONFORMANT PLANNING ⋮ A Sufficient Statistic for Influence in Structured Multiagent Environments ⋮ Equivalence notions and model minimization in Markov decision processes ⋮ Solving factored MDPs using non-homogeneous partitions ⋮ Constraint solving in uncertain and dynamic environments: A survey

Uses Software

• UCPOP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning for conjunctive goals
• Symbolic model checking: \(10^{20}\) states and beyond
• Constructing optimal binary decision trees is NP-complete
• Probabilistic Horn abduction and Bayesian networks
• Modeling a dynamic and uncertain world. I: Symbolic and probabilistic reasoning about change
• Trading accuracy for simplicity in decision trees
• The independent choice logic for modelling multiple agents under uncertainty
• Abstraction and approximate decision-theoretic planning.
• \({\mathcal Q}\)-learning
• Transfer of learning by composing solutions of elemental sequential tasks
• The role of relevance in explanation. I: Irrelevance as statistical independence
• STRIPS: A new approach to the application of theorem proving to problem solving
• A survey of algorithmic methods for partially observed Markov decision processes
• Dynamic programming and influence diagrams
• Iterative Aggregation-Disaggregation Procedures for Discounted Semi-Markov Reward Processes
• Automatic verification of finite-state concurrent systems using temporal logic specifications
• Graph-Based Algorithms for Boolean Function Manipulation
• Adaptive aggregation methods for infinite horizon dynamic programming
• Guarded commands, nondeterminacy and formal derivation of programs
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon