POMDP controllers with optimal budget

DOI10.1007/978-3-031-16336-4_6MaRDI QIDQ6160772zbMATH OpenFDO

Authors Jip Spel, Svenja Stein, Joost-Pieter Katoen

Publication date 2 June 2023

Published in Quantitative Evaluation of Systems (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-16336-4_6

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Markov and semi-Markov decision processes (90C40)

Recommendations

• Optimal cost almost-sure reachability in POMDPs
• On Near Optimality of the Set of Finite-State Controllers for Average Cost POMDP
• On the Computational Complexity of Stochastic Controller Optimization in POMDPs
• Control Theory Meets POMDPs: A Hybrid Systems Approach
• Efficient Algorithms for Budget-Constrained Markov Decision Processes
• Policy iteration for bounded-parameter POMDPs
• Efficient, optimal stochastic-action selection when limited by an action budget
• Partially observable stochastic optimal control
• scientific article; zbMATH DE number 18469
• Optimal control with budget constraints and resets

Cites work

• Accelerated model checking of parametric Markov chains
• Are parametric Markov chains monotonic?
• Computationally Feasible Bounds for Partially Observed Markov Decision Processes
• Finding provably optimal Markov chains
• scientific article; zbMATH DE number 1509479 (Why is no real title available?)
• scientific article; zbMATH DE number 783783 (Why is no real title available?)
• scientific article; zbMATH DE number 5585443 (Why is no real title available?)
• Parameter synthesis for Markov models: faster than ever
• Parametric Markov chains: PCTL complexity and fraction-free Gaussian elimination
• Parametric Markov chains: PCTL complexity and fraction-free Gaussian elimination
• Parametric probabilistic transition systems for system design and analysis
• Perturbation analysis in verification of discrete-time Markov chains
• Planning and acting in partially observable stochastic domains
• Reinforcement learning with limited reinforcement: using Bayes risk for active learning in POMDPs
• The complexity of reachability in parametric Markov decision processes
• Theoretical Aspects of Computing - ICTAC 2004

Cited in

(3)

• On the Computational Complexity of Stochastic Controller Optimization in POMDPs
• Control Theory Meets POMDPs: A Hybrid Systems Approach
• Parameter-Independent Strategies for pMDPs via POMDPs

This page was built for publication: POMDP controllers with optimal budget

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6160772)