Efficient approximate planning in continuous space Markovian decision problems

MaRDI QIDQ2758704zbMATH OpenFDO

Authors Csaba Szepesvári

Publication date 2 May 2002

Published in AI Communications (Search for Journal in Brave)

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Markov and semi-Markov decision processes (90C40)

Recommendations

• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• On the asymptotic optimality of finite approximations to Markov decision processes with Borel spaces
• Monte Carlo value iteration for continuous-state POMDPS
• Abstraction and approximate decision-theoretic planning.
• scientific article; zbMATH DE number 2000828

Cited in

(5)

• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Proximity-based non-uniform abstractions for approximate planning
• Barycentric quantization for planning in continuous domains
• Sample-based planning and learning with function approximation
• Weighted mesh algorithms for general Markov decision processes: convergence and tractability

This page was built for publication: Efficient approximate planning in continuous space Markovian decision problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2758704)