On the Rate of Convergence of Fictitious Play

DOI10.1007/978-3-642-16170-4_10zbMath1310.91032OpenAlexW3136807736MaRDI QIDQ3162511

Paul Harrenstein, Felix Brandt, Felix Fischer

Publication date: 19 October 2010

Published in: Algorithmic Game Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-642-16170-4_10

Mathematics Subject Classification ID

Noncooperative games (91A10) Rationality and learning in game theory (91A26) Evolutionary games (91A22)

Related Items

On Best-Response Dynamics in Potential Games, On the approximation performance of fictitious play in finite games, Fictitious play with incomplete learning, Near-optimal no-regret algorithms for zero-sum games

Uses Software

• AWESOME

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency and cautious fictitious play
• ``Evolutionary selection dynamic in games: Convergence and limit properties
• Learning in games with strategic complementarities revisited
• Brown's original fictitious play
• Fictitious play in \(2\times n\) games
• Potential games
• A \(2 \times 2\) game without the fictitious play property
• The rate of convergence of continuous fictitious play
• Fictitious play property for games with identical interests
• The convergence of fictitious play in \(3\times\)3 games with strategic complementarities
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• An iterative method of solving a game
• On the Hardness and Existence of Quasi-Strict Equilibria