Discounted Markov games: Generalized policy iteration method

DOI10.1007/BF00933260zbMath0352.90071OpenAlexW51114640MaRDI QIDQ1236071

K. Appert

Publication date: 1978

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00933260

Mathematics Subject Classification ID

2-person games (91A05) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Related Items (10)

A short certificate of the number of universal optimal strategies for stopping simple stochastic games ⋮ Numerical methods for dynamic Bertrand oligopoly and American options under regime switching ⋮ (Approximate) iterated successive approximations algorithm for sequential decision processes ⋮ On the complexity of computational problems associated with simple stochastic games ⋮ Policy iteration algorithms for zero-sum stochastic differential games with long-run average payoff criteria ⋮ Value set iteration for two-person zero-sum Markov games ⋮ Unnamed Item ⋮ Improved iterative computation of the expected discounted return in Markov and semi-Markov chains ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms ⋮ Piecewise constant policy approximations to Hamilton-Jacobi-Bellman equations

Cites Work

• Unnamed Item
• Unnamed Item
• Discounted Markov games; successive approximation and stopping times
• A modified dynamic programming method for Markovian decision problems
• On Markov games
• A set of successive approximation methods for discounted Markovian decision problems
• On Nonterminating Stochastic Games
• On some stocxastic tactical antisubmarine games
• Algorithms for Stochastic Games with Geometrical Interpretation
• Some Bounds for Discounted Sequential Decision Processes
• Stochastic Games

This page was built for publication: Discounted Markov games: Generalized policy iteration method