Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information
From MaRDI portal
Publication:433846
DOI10.1016/j.orl.2011.10.005zbMath1243.91010OpenAlexW2149125186MaRDI QIDQ433846
Lorenzo Maggi, Laura Cottatellucci, Konstantin E. 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
stochastic gamesperfect informationmulti-agent Markov decision processesoptimality rangeuniform optimal strategies
Related Items
Confidence intervals for the Shapley-Shubik power index in Markovian games, Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs
Cites Work
- Sensitivity analysis in discounted Markovian decision problems
- Ordered field property for stochastic games when the player who controls transitions changes from state to state
- Asymptotic linear programming and policy improvement for singularly perturbed Markov decision processes
- 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