Simulation‐based Uniform Value Function Estimates of Markov Decision Processes

DOI10.1137/040619508MaRDI QIDQ3593009zbMATH OpenOpenAlexFDO

Authors Rahul Jain, Pravin Varaiya

Publication date 24 September 2007

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/040619508

zbMATH Keywords

Markov decision processesMarkov gamesPAC learningempirical process theoryuniform rate of convergencevalue function estimation

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Empirical decision procedures; empirical Bayes procedures (62C12) Markov and semi-Markov decision processes (90C40)

Recommendations

• The value functions of Markov decision processes
• Simulation-based algorithms for Markov decision processes
• scientific article; zbMATH DE number 1509479
• Simulation-based optimization of Markov reward processes
• Uniform convergence of value iteration policies for discounted Markov decision processes
• Computing optimal policies for Markovian decision processes using simulation
• scientific article; zbMATH DE number 3916050
• Simulation-based optimization of Markov decision processes: an empirical process theory approach
• A class of procedures to compute the optimal value f unction in a Markovian decision problem

Cited in

(9)

• A survey of some simulation-based algorithms for Markov decision processes
• Bias and variance approximation in value function estimates
• Empirical dynamic programming
• Simulation-based optimization of Markov decision processes: an empirical process theory approach
• On the convergence of reinforcement learning with Monte Carlo exploring starts
• CONVERGENCE OF SIMULATION-BASED POLICY ITERATION
• Computing optimal policies for Markovian decision processes using simulation
• scientific article; zbMATH DE number 1804129 (Why is no real title available?)
• Near optimality of quantized policies in stochastic control under weak continuity conditions

This page was built for publication: Simulation‐based Uniform Value Function Estimates of Markov Decision Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3593009)