Equivalence notions and model minimization in Markov decision processes

DOI10.1016/S0004-3702(02)00376-4zbMath1082.68801MaRDI QIDQ814474

N. E. Zubov

Publication date: 7 February 2006

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

zbMATH Keywords

Markov decision processesBisimulationKnowledge representationFactored state spacesState abstractionStochastic planning

Mathematics Subject Classification ID

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

Related Items (19)

Robust Control for Dynamical Systems with Non-Gaussian Noise via Formal Abstractions ⋮ Approximation metrics based on probabilistic bisimulations for general state-space Markov processes: a survey ⋮ Extreme state aggregation beyond Markov decision processes ⋮ Adaptive aggregation for reinforcement learning in average reward Markov decision processes ⋮ A uniform framework for modeling nondeterministic, probabilistic, stochastic, or mixed processes and their behavioral equivalences ⋮ Algebraic decompositions of DP problems with linear dynamics ⋮ A taxonomy for similarity metrics between Markov decision processes ⋮ Planning in hybrid relational MDPs ⋮ Mixed nondeterministic-probabilistic automata: blending graphical probabilistic models with nondeterminism ⋮ Pseudometrics for State Aggregation in Average Reward Markov Decision Processes ⋮ Exact finite approximations of average-cost countable Markov decision processes ⋮ Exploiting symmetries for single- and multi-agent partially observable stochastic domains ⋮ Regret bounds for restless Markov bandits ⋮ Unnamed Item ⋮ Relevant states and memory in Markov chain bootstrapping and simulation ⋮ Model Refinement Using Bisimulation Quotients ⋮ Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices ⋮ Unnamed Item ⋮ A Sufficient Statistic for Influence in Structured Multiagent Environments

Cites Work

• Bisimulation through probabilistic testing
• Minimal state graph generation
• Optimal control of diffusion processes with reflection
• Modeling a dynamic and uncertain world. I: Symbolic and probabilistic reasoning about change
• Abstraction and approximate decision-theoretic planning.
• Stochastic dynamic programming with factored representations
• Algebraic laws for nondeterminism and concurrency
• Finite Continuous Time Markov Chains
• State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

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