Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information

DOI10.1016/J.ORL.2011.10.005MaRDI QIDQ433846zbMATH OpenOpenAlexFDO

Authors Laura Cottatellucci, Lorenzo Maggi, Konstantin Avrachenkov

Publication date 6 July 2012

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

Full work available at URL https://hal.inria.fr/inria-00506390/file/RR-7355.pdf

zbMATH Keywords

perfect informationstochastic gamesmulti-agent Markov decision processesoptimality rangeuniform optimal strategies

Mathematics Subject Classification ID

2-person games (91A05) Stochastic games, stochastic differential games (91A15)

Recommendations

• Computing uniformly optimal strategies in two-player stochastic games
• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• New algorithms for solving zero-sum stochastic games
• scientific article; zbMATH DE number 1944075
• Algorithms for stochastic games ? A survey

Cites work

• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• An asymptotic simplex method for singularly perturbed linear programs
• Asymptotic Linear Programming
• Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
• Ordered field property for stochastic games when the player who controls transitions changes from state to state
• Sensitivity analysis in discounted Markovian decision problems

Cited in

(10)

• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• Confidence intervals for the Shapley-Shubik power index in Markovian games
• New algorithms for solving zero-sum stochastic games
• Playing in stochastic environment: from multi-armed bandits to two-player games
• Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information
• Computing uniformly optimal strategies in two-player stochastic games
• scientific article; zbMATH DE number 4102846 (Why is no real title available?)
• Optimal comparison strategies in Ulam's searching game with two errors
• Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs
• scientific article; zbMATH DE number 1507326 (Why is no real title available?)

This page was built for publication: Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q433846)