A policy improvement algorithm for solving a mixture class of perfect information and AR-at semi-Markov games

DOI10.1142/S0219198920400083zbMATH Open1494.91010OpenAlexW3004819735WikidataQ114978461 ScholiaQ114978461MaRDI QIDQ5149581FDOQ5149581

Authors: P. Mondal, S. K. Neogy, Debasish Ghorui, Abhijit Kar Gupta 

Publication date: 11 February 2021

Published in: International Game Theory Review (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219198920400083

Recommendations

• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs
• Zero-sum two-person semi-Markov games
• Discounted semi-Markov games and algorithms for solving two structured classes
• On discounted AR-AT semi-Markov games and its complementarity formulations

zbMATH Keywords

perfect informationAR-ATsemi-Markov gamesoptimal pure stationary strategiespolicy improvement algorithm

Mathematics Subject Classification ID

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

Cites Work

• Title not available (Why is that?)
• Stochastic Games
• Perfect information stochastic games and related classes
• Algorithms for stochastic games ? A survey
• Title not available (Why is that?)
• On stochastic games with additive reward and transition structure
• Ordered field property for semi-Markov games when one player controls transition probabilities and transition times
• Markov-Renewal Programming. I: Formulation, Finite Return Models
• Title not available (Why is that?)
• Discrete Dynamic Programming
• Zero-sum semi-Markov games in Borel spaces: Discounted and average payoff
• Vertical linear complementarity and discounted zero-sum stochastic games with ARAT structure
• Pivoting algorithms for some classes of stochastic games: A survey
• On discounted AR-AT semi-Markov games and its complementarity formulations
• Existence of p-Equilibrium and Optimal Stationary Strategies in Stochastic Games
• ORDERED FIELD PROPERTY IN A SUBCLASS OF FINITE SER-SIT SEMI-MARKOV GAMES
• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• Ordered field property for stochastic games when the player who controls transitions changes from state to state
• Zero-sum two-person semi-Markov games
• Completely mixed strategies for two structured classes of semi-Markov games, principal pivot transform and its generalizations

Cited In (4)

• Policy improvement for perfect information additive reward and additive transition stochastic games with discounted and average payoffs
• Discounted semi-Markov games and algorithms for solving two structured classes
• Zero-sum semi-Markov games with state-action-dependent discount factors
• Completely mixed strategies for two structured classes of semi-Markov games, principal pivot transform and its generalizations

This page was built for publication: A policy improvement algorithm for solving a mixture class of perfect information and AR-at semi-Markov games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5149581)