Approximate policy iteration for Markov decision processes via quantitative adaptive aggregations

DOI10.1007/978-3-319-46520-3_2MaRDI QIDQ1990495zbMATH OpenOpenAlexFDO

Authors Alessandro Abate, Milan Češka, Marta Kwiatkowska

Publication date 25 October 2018

Full work available at URL https://doi.org/10.1007/978-3-319-46520-3_2

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• scientific article; zbMATH DE number 3871063
• Approximation of infinite horizon discounted cost Markov decision processes
• A time aggregation approach to Markov decision processes
• On the asymptotic optimality of finite approximations to Markov decision processes with Borel spaces
• Approximation of Markov decision processes with general state space

Cited in

(11)

• Approximate dynamic programming with state aggregation applied to UAV perimeter patrol
• Approximate Newton methods for policy search in Markov decision processes
• Introduction to internally consistent modeling, aggregation, inference, and policy
• scientific article; zbMATH DE number 4133249 (Why is no real title available?)
• On State Aggregation to Approximate Complex Value Functions in Large-Scale Markov Decision Processes
• A low-rank approximation for MDPs via moment coupling
• Dynamic policy programming
• Relative value iteration algorithm with soft state aggregation
• Aggregation of the policy iteration method for nearly completely decomposable Markov chains
• Optimal learning with \textit{Q}-aggregation
• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes

This page was built for publication: Approximate policy iteration for Markov decision processes via quantitative adaptive aggregations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1990495)