A Folk Theorem from Learning
We introduce state-dependent smooth fictitious play and we use this learning algorithm to prove a Folk theorem for repeated potential games. Our result shows that decentralised learning algorithms can learn to collude through repeated interactions and without communication.
Date:
3 March 2023, 12:45 (Friday, 7th week, Hilary 2023)
Venue:
Manor Road Building, Manor Road OX1 3UQ
Venue Details:
Seminar Room G or join online: https://zoom.us/j/96595245637
Speaker:
Patrick Chang (University of Oxford)
Organising department:
Department of Economics
Part of:
Student Research Workshop in Micro Theory
Booking required?:
Not required
Audience:
Members of the University only
Editor:
Emma Heritage
