Regret, Equilibrium, and Learning in Games: A Comprehensive Survey

bronzeagepapi · x · 2026-08-12

Panayotis Mertikopoulos published a survey on learning theory in games, bridging machine learning and economics. The paper covers both single-agent sequential decision-making in adversarial environments and multi-agent interactions.

It focuses on regularized learning policies that encourage exploration via penalties. Key contributions include regret bounds for adversarial multi-armed bandits, equilibrium convergence results in zero-sum games, and a 'folk theorem' linking Nash equilibria to the stability of learning dynamics.

Original post →

More from Research

Research channel →