Stochastic dynamic programming with factored representations

DOI10.1016/S0004-3702(00)00033-3zbMATH Open0948.68167WikidataQ126771357 ScholiaQ126771357MaRDI QIDQ1583230FDOQ1583230

Authors: Craig Boutilier, Richard Dearden, Moisés Goldszmidt 

Publication date: 26 October 2000

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

Recommendations

• Abstraction and approximate decision-theoretic planning.
• scientific article; zbMATH DE number 1315585
• scientific article; zbMATH DE number 2000828
• Planning and acting in partially observable stochastic domains
• Influence of modeling structure in probabilistic sequential decision problems

zbMATH Keywords

regressionBayesian networksdecision treesabstractionMarkov decision processesdecision-theoretic planning

Mathematics Subject Classification ID

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

Cites Work

• A survey of algorithmic methods for partially observed Markov decision processes
• Title not available (Why is that?)
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Title not available (Why is that?)
• The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
• Title not available (Why is that?)
• Graph-Based Algorithms for Boolean Function Manipulation
• \({\mathcal Q}\)-learning
• Title not available (Why is that?)
• Planning for conjunctive goals
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Symbolic model checking: \(10^{20}\) states and beyond
• STRIPS: A new approach to the application of theorem proving to problem solving
• Automatic verification of finite-state concurrent systems using temporal logic specifications
• The independent choice logic for modelling multiple agents under uncertainty
• Guarded commands, nondeterminacy and formal derivation of programs
• Title not available (Why is that?)
• Title not available (Why is that?)
• Probabilistic Horn abduction and Bayesian networks
• Constructing optimal binary decision trees is NP-complete
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Adaptive aggregation methods for infinite horizon dynamic programming
• Feature-based methods for large scale dynamic programming
• Dynamic programming and influence diagrams
• Title not available (Why is that?)
• Abstraction and approximate decision-theoretic planning.
• Title not available (Why is that?)
• Modeling a dynamic and uncertain world. I: Symbolic and probabilistic reasoning about change
• Trading accuracy for simplicity in decision trees
• Transfer of learning by composing solutions of elemental sequential tasks
• Iterative Aggregation-Disaggregation Procedures for Discounted Semi-Markov Reward Processes
• The role of relevance in explanation. I: Irrelevance as statistical independence

Cited In (48)

• Analysis of customer lifetime value and marketing expenditure decisions through a Markovian-based model
• Elaboration tolerant representation of Markov decision process via decision-theoretic extension of probabilistic action language \(p\mathcal{BC}+\)
• The factored policy-gradient planner
• Decision-theoretic planning with generalized first-order decision diagrams
• Discovering hidden structure in factored MDPs
• Equivalence notions and model minimization in Markov decision processes
• 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 framework and a mean-field algorithm for the local control of spatial processes
• A Verified Compositional Algorithm for AI Planning
• Proximity-based non-uniform abstractions for approximate planning
• A POMDP framework for coordinated guidance of autonomous UAVs for multitarget tracking
• A sufficient statistic for influence in structured multiagent environments
• Planning in artificial intelligence
• Reinforcement learning
• Complexity results and algorithms for possibilistic influence diagrams
• Embedding a state space model into a Markov decision process
• AI 2005: Advances in Artificial Intelligence
• Automatic induction of Bellman-error features for probabilistic planning
• Algebraic decompositions of DP problems with linear dynamics
• Solving factored mdps with hybrid state and action variables
• Agent's actions as a classification criteria for the state space in a learning from rewards system
• Policy iteration based on stochastic factorization
• Abstraction and approximate decision-theoretic planning.
• Title not available (Why is that?)
• Junction Tree Factored Particle Inference Algorithm for Multi-Agent Dynamic Influence Diagrams
• Efficient algorithms for risk-sensitive Markov decision processes with limited budget
• Influence of modeling structure in probabilistic sequential decision problems
• Learning classifier systems: a survey
• Rethinking formal models of partially observable multiagent decision making
• Solving factored MDPs using non-homogeneous partitions
• Intensional dynamic programming. A rosetta stone for structured dynamic programming
• Exploiting expert knowledge in factored POMDPs
• Representing value functions with recurrent binary decision diagrams
• Symmetric approximate linear programming for factored MDPs with application to constrained problems
• Efficient approximate linear programming for factored MDPs
• Real-time dynamic programming for Markov decision processes with imprecise probabilities
• Efficient incremental planning and learning with multi-valued decision diagrams
• Scalable transfer learning in heterogeneous, dynamic environments
• Title not available (Why is that?)
• Reinforcement learning with factored states and actions
• Action failure recovery via model-based diagnosis and conformant planning
• The interaction of representations and planning objectives for decision-theoretic planning tasks
• Title not available (Why is that?)
• Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning
• Probabilistic relational planning with first order decision diagrams
• Constraint solving in uncertain and dynamic environments: A survey
• Efficient solutions to factored MDPs with imprecise transition probabilities

Uses Software

• UCPOP

This page was built for publication: Stochastic dynamic programming with factored representations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1583230)