Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs

DOI10.3934/JDG.2014.1.347MaRDI QIDQ482541zbMATH OpenOpenAlexFDO

Authors Matthew Bourque, Thirukkannamangai E. S. Raghavan

Publication date 5 January 2015

Published in Journal of Dynamics and Games (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/jdg.2014.1.347

zbMATH Keywords

Markov decision processperfect informationstochastic gamespolicy iterationadditive reward additive transition

Mathematics Subject Classification ID

2-person games (91A05) Markov and semi-Markov decision processes (90C40) Stochastic games, stochastic differential games (91A15)

Recommendations

• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• A policy iteration algorithm for zero-sum stochastic games with mean payoff
• scientific article; zbMATH DE number 1944075
• A policy improvement algorithm for solving a mixture class of perfect information and AR-at semi-Markov games
• Publication:4504053

Cites work

• scientific article; zbMATH DE number 3145626 (Why is no real title available?)
• scientific article; zbMATH DE number 3148886 (Why is no real title available?)
• scientific article; zbMATH DE number 18886 (Why is no real title available?)
• scientific article; zbMATH DE number 1134975 (Why is no real title available?)
• A policy iteration algorithm for zero-sum stochastic games with mean payoff
• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information
• An orderfield property for stochastic games when one player controls transition probabilities
• Asymptotic Linear Programming
• Discrete Dynamic Programming
• Invariant Half-Lines of Nonexpansive Piecewise-Linear Transformations
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• On stochastic games with additive reward and transition structure
• Scientific Applications: An algorithm for identifying the ergodic subchains and transient states of a stochastic matrix
• Sensitivity analysis in discounted Markovian decision problems
• Stochastic Games
• Stochastic games have a value

Cited in

(6)

• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• Policy invariance under reward transformations for general-sum stochastic games
• A policy improvement algorithm for solving a mixture class of perfect information and AR-at semi-Markov games
• Generic uniqueness of the bias vector of finite zero-sum stochastic games with perfect information
• The relationships between discounted and average criteria of stochastic games with prospect theory
• scientific article; zbMATH DE number 1507326 (Why is no real title available?)

This page was built for publication: Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q482541)