Generalised weakened fictitious play

DOI10.1016/j.geb.2005.08.005zbMath1177.91044OpenAlexW2167957526MaRDI QIDQ2507678

E. J. Collins, David S. Leslie

Publication date: 5 October 2006

Published in: Games and Economic Behavior (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.geb.2005.08.005

zbMATH Keywords

stochastic approximationfictitious playactor--critic processbest response differential inclusion

Mathematics Subject Classification ID

Ordinary differential inclusions (34A60) Multistage and repeated games (91A20) Actuarial science and mathematical finance (91G99)

Related Items (14)

On Best-Response Dynamics in Potential Games ⋮ Multi-rate threshold FlipThem ⋮ Fictitious Play in Zero-Sum Stochastic Games ⋮ Robustness Properties in Fictitious-Play-Type Algorithms ⋮ Value functions for depth-limited solving in zero-sum imperfect-information games ⋮ Learning and equilibrium transitions: stochastic stability in discounted stochastic fictitious play ⋮ A unified stochastic approximation framework for learning in games ⋮ Convergence in games with continua of equilibria ⋮ Best-response dynamics in zero-sum stochastic games ⋮ Decentralized MDPs with sparse interactions ⋮ Emergence of information transfer by inductive learning ⋮ Learning in games with strategic complementarities revisited ⋮ Fictitious play property of the Nash demand game ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fictitious play applied to sequences of games and discounted stochastic games
• Evolutionarily stable strategies and game dynamics
• Learning mixed equilibria
• Learning through reinforcement and replicator dynamics
• Learning, hypothesis testing, and Nash equilibrium.
• Convergent multiple-timescales reinforcement learning algorithms in normal form games
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Fictitious play in \(2\times n\) games
• On the convergence of reinforcement learning
• Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
• Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term
• Fictitious play property for games with identical interests
• Learning in perturbed asymmetric games
• Attainability of boundary points under reinforcement learning
• An iterative method of solving a game
• A WEAKENED FORM OF FICTITIOUS PLAY IN TWO-PERSON ZERO-SUM GAMES
• Social Stability and Equilibrium
• Evolutionary Games and Population Dynamics
• Stochastic Approximations and Differential Inclusions
• Individual Q-Learning in Normal Form Games
• On the Global Convergence of Stochastic Fictitious Play

This page was built for publication: Generalised weakened fictitious play