Equivalence notions and model minimization in Markov decision processes

DOI10.1016/S0004-3702(02)00376-4zbMATH Open1082.68801MaRDI QIDQ814474FDOQ814474

Authors: N. E. Zubov 

Publication date: 7 February 2006

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

Recommendations

• Approximate equivalence of Markov decision processes.
• Stochastic dynamic programming with factored representations
• Abstraction and approximate decision-theoretic planning.
• Solving factored MDPs using non-homogeneous partitions
• scientific article; zbMATH DE number 2086977

zbMATH Keywords

Markov decision processesBisimulationKnowledge representationFactored state spacesState abstractionStochastic planning

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Reasoning under uncertainty in the context of artificial intelligence (68T37) Knowledge representation (68T30)

Cites Work

• Title not available (Why is that?)
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• Title not available (Why is that?)
• Algebraic laws for nondeterminism and concurrency
• Title not available (Why is that?)
• Title not available (Why is that?)
• Bisimulation through probabilistic testing
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Optimal control of diffusion processes with reflection
• Finite Continuous Time Markov Chains
• Stochastic dynamic programming with factored representations
• Abstraction and approximate decision-theoretic planning.
• Minimal state graph generation
• Modeling a dynamic and uncertain world. I: Symbolic and probabilistic reasoning about change

Cited In (25)

• Approximation metrics based on probabilistic bisimulations for general state-space Markov processes: a survey
• Relevant states and memory in Markov chain bootstrapping and simulation
• Pseudometrics for State Aggregation in Average Reward Markov Decision Processes
• A uniform framework for modeling nondeterministic, probabilistic, stochastic, or mixed processes and their behavioral equivalences
• Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions
• A sufficient statistic for influence in structured multiagent environments
• Planning in artificial intelligence
• Title not available (Why is that?)
• Structure in machine learning
• Exploiting symmetries for single- and multi-agent partially observable stochastic domains
• Regret bounds for restless Markov bandits
• Algebraic decompositions of DP problems with linear dynamics
• Extreme state aggregation beyond Markov decision processes
• The complexity of graph-based reductions for reachability in Markov decision processes
• Title not available (Why is that?)
• Model refinement using bisimulation quotients
• Abstraction and approximate decision-theoretic planning.
• Mixed nondeterministic-probabilistic automata: blending graphical probabilistic models with nondeterminism
• Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices
• A taxonomy for similarity metrics between Markov decision processes
• Title not available (Why is that?)
• Planning in hybrid relational MDPs
• Exact finite approximations of average-cost countable Markov decision processes
• Approximate equivalence of Markov decision processes.
• Adaptive aggregation for reinforcement learning in average reward Markov decision processes

This page was built for publication: Equivalence notions and model minimization in Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q814474)