Long-Term Values in Markov Decision Processes and Repeated Games, and a New Distance for Probability Spaces

DOI10.1287/MOOR.2016.0814zbMath1364.90350OpenAlexW2557272457MaRDI QIDQ5739144

Jérôme Renault, Xavier Venel

Publication date: 2 June 2017

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/11385/197395

zbMATH Keywords

Wasserstein metricrepeated gamesuniform valuegambling housescharacterization of the valuepartial observation Markov decision processes

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic games, stochastic differential games (91A15) Markov and semi-Markov decision processes (90C40)

Related Items (11)

General limit value in zero-sum stochastic games ⋮ Turnpike in optimal control of PDEs, ResNets, and beyond ⋮ Finite-Memory Strategies in POMDPs with Long-Run Average Objectives ⋮ Limit value for optimal control with general means ⋮ Long information design ⋮ Value‐based distance between information structures ⋮ Representation Formulas for Limit Values of Long Run Stochastic Optimal Controls ⋮ Repeated Games with Incomplete Information ⋮ Asymptotics of values in dynamic games on large intervals ⋮ Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes ⋮ History-dependent Evaluations in Partially Observable Markov Decision Process

This page was built for publication: Long-Term Values in Markov Decision Processes and Repeated Games, and a New Distance for Probability Spaces