Fictitious play in stochastic games

DOI10.1007/S00186-007-0158-9MaRDI QIDQ2472192zbMATH OpenOpenAlexFDO

Authors G. Schoenmakers, Frank Thuijsman, János Flesch

Publication date 20 February 2008

Published in Mathematical Methods of Operations Research (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://doi.org/10.1007/s00186-007-0158-9

zbMATH Keywords

fictitious playNon-cooperative gamesstochastic games

Mathematics Subject Classification ID

Noncooperative games (91A10) Stochastic games, stochastic differential games (91A15) Rationality and learning in game theory (91A26) Stochastic learning and adaptive control (93E35)

Review text

An explicit example of a stochastic game is considered, with two players, two states and two actions, and with special structure such as single controller condition, irreducibility, and state-independent transitions. This has a unique equilibrium in stationary strategies. It is shown that even in this apparently simple situation, fictitious play, wherein a player always plays her best response to the opponent's empirical policy, does not converge.

Recommendations

• Fictitious play in zero-sum stochastic games
• Fictitious play for continuous games
• Fictitious play in \(2\times n\) games
• Fictitious play for continuous games revisited
• Fictitious play in extensive form games
• Fictitious play in one-against-all multi-player games
• Fictitious play in coordination games
• Stochastic fictitious play with continuous action sets
• Fictitious play in 2 3 games

Cites work

• An iterative method of solving a game
• Fictitious play applied to sequences of games and discounted stochastic games
• Fictitious play in \(2\times 2\) games: A geometric proof of convergence
• Fictitious play in 2 3 games
• Fictitious play property for games with identical interests
• scientific article; zbMATH DE number 3128733 (Why is no real title available?)
• scientific article; zbMATH DE number 3205074 (Why is no real title available?)
• Noncooperative Stochastic Games
• On the convergence of fictitious play.
• Ordered field property for stochastic games when the player who controls transitions changes from state to state
• Semi-Markov strategies in stochastic games
• Stochastic Games
• Two-player stochastic games. I: A reduction
• Two-player stochastic games. II: The case of recursive games

Cited in

(17)

• On the nonconvergence of fictitious play in coordination games
• Fictitious play in coordination games
• Fictitious play in \(2\times n\) games
• Fictitious play in extensive form games
• A \(2 \times 2\) game without the fictitious play property
• Fictitious play in one-against-all multi-player games
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Fictitious play by cases
• The convergence of fictitious play in games with strategic complementarities
• Best-response dynamics in zero-sum stochastic games
• Fictitious play property of the Nash demand game
• Fictitious play in zero-sum stochastic games
• Sampled fictitious play for approximate dynamic programming
• On the Global Convergence of Stochastic Fictitious Play
• Fictitious play for continuous games
• Fictitious play in 3 3 games: chaos and dithering behaviour
• Fictitious play in an evolutionary environment

This page was built for publication: Fictitious play in stochastic games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2472192)