Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances
DOI10.1007/s13235-018-0253-yzbMath1411.91053OpenAlexW2791319380MaRDI QIDQ1741211
François Dufour, Tomás Prieto-Rumeau
Publication date: 3 May 2019
Published in: Dynamic Games and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s13235-018-0253-y
Wasserstein distanceminimax control problemapproximation of control modelsrobust Markov decision process
Minimax problems in mathematical programming (90C47) 2-person games (91A05) Stochastic games, stochastic differential games (91A15) Markov and semi-Markov decision processes (90C40)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Computable approximations for continuous-time Markov decision processes on Borel spaces based on empirical measures
- A perturbation approach to a class of discounted approximate value iteration algorithms with Borel spaces
- Robust Markov control processes
- Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
- Approximation of Markov decision processes with general state space
- Stochastic games with unbounded payoffs: applications to robust control in economics
- Simulation-based algorithms for Markov decision processes.
- Approximation of zero-sum continuous-time Markov games under the discounted payoff criterion
- Approximation of two-person zero-sum continuous-time Markov games with average payoff criterion
- Stochastic approximations of constrained discounted Markov decision processes
- A policy iteration algorithm for zero-sum stochastic games with mean payoff
- Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces
- Minimax Control of Discrete-Time Stochastic Systems
- Multigrid methods for two‐player zero‐sum stochastic games
- Approximation of average cost Markov decision processes using empirical distributions and concentration inequalities
- Approximate Dynamic Programming
- Minimax Theorems
This page was built for publication: Approximation of discounted minimax Markov control problems and zero-sum Markov games using Hausdorff and Wasserstein distances
