Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information

DOI10.1287/MOOR.6.3.379MaRDI QIDQ3316995zbMATH OpenOpenAlexFDO

Authors S. Lakshmivarahan, K. S. Narendra

Publication date 1981

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

Full work available at URL https://doi.org/10.1287/moor.6.3.379

zbMATH Keywords

incomplete informationlearning algorithmsMarkov processoptimal pure strategiestwo-person zero-sum sequential stochastic game

Mathematics Subject Classification ID

2-person games (91A05) Stochastic games, stochastic differential games (91A15) Probabilistic games; gambling (91A60)

Recommendations

• A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum Stochastic Games
• Learning algorithms for repeated bimatrix Nash games with incomplete information
• scientific article; zbMATH DE number 3920249
• A policy-improvement type algorithm for solving zero-sum two-person stochastic games of perfect information
• A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
• Learning with minimal information in continuous games
• Algorithms for uniform optimal strategies in two-player zero-sum stochastic games with perfect information
• On learning algorithms for Nash equilibria
• Use of learning automata for stochastic games with incomplete information
• Stability of learning dynamics in two-agent, imperfect-information games

Cited in

(12)

• Learning models for decentralized decision making
• Learning through reinforcement and replicator dynamics
• A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
• The lagging anchor algorithm: Reinforcement learning in two-player zero-sum games with imperfect information
• Learning behavior of variable-structure stochastic automata in a three-person zero-sum game
• scientific article; zbMATH DE number 3920249 (Why is no real title available?)
• Distributed learning of the global maximum in a two-player stochastic game with identical payoffs
• Use of learning automata for stochastic games with incomplete information
• Stability of learning dynamics in two-agent, imperfect-information games
• Learning automata based multi-agent system algorithms for finding optimal policies in Markov games
• Adaptive policy for two finite Markov chains zero-sum stochastic game with unknown transition matrices and average payoffs
• Adaptive approaches to stochastic programming

This page was built for publication: Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3316995)