Estimating the value of a discounted reward process

DOI10.1016/0167-6377(92)90002-KzbMath0771.62043OpenAlexW2044252233MaRDI QIDQ1196212

Martin L. Puterman, Moshe Haviv

Publication date: 17 December 1992

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6377(92)90002-k

zbMATH Keywords

differential equationsimulationsunbiased estimatordiscounted reward processexpected total discounted returnexpected total discounted rewardexpected total undiscounted returnindependent negative binomial stopping timessampling cumulative sums of the rewardsvariance properties

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Inference from stochastic processes (62M99) Markov and semi-Markov decision processes (90C40)

Cites Work

• Finite state Markovian decision processes
• Simulating Discounted Costs

This page was built for publication: Estimating the value of a discounted reward process