Reinforcement Learning, Collusion, and the Folk Theorem

2024/11/19 by Askenazi-Golan, Galit, Cecchelli, Domenico Mergoni, Plumb, Edward
#Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #FOS: Economics and business #Machine Learning (stat.ML) #Theoretical Economics (econ.TH)

paper · doi:10.48550/arxiv.2411.12725

Abstract

We explore the behaviour emerging from learning agents repeatedly interacting strategically for a wide range of learning dynamics that includes projected gradient, replicator and log-barrier dynamics. Going beyond the better-understood classes of potential games and zero-sum games, we consider the setting of a general repeated game with finite recall, for different forms of monitoring. We obtain a Folk Theorem-like result and characterise the set of payoff vectors that can be obtained by these dynamics, discovering a wide range of possibilities for the emergence of algorithmic collusion.

Related

• Robust Algorithmic Collusion
• Towards a taxonomy of learning dynamics in 2 x 2 games
• Uncoupled Learning Rules for Seeking Equilibria in Repeated Plays: An Overview
• Stochastic Collusion and the Power Law of Learning
• Learning in Multi-Memory Games Triggers Complex Dynamics Diverging from Nash Equilibrium