SOURCE-LINKED INTELLIGENCE

Mitigating Retaliatory Algorithmic Collusion in Repeated Games

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Reinforcement learning agents trained to maximize their own reward in repeated interactions can converge to supra-competitive outcomes resembling explicit collusion, without communication or shared design. Existing mitigation approaches are largely tied to specific economic settings, like two-sided platforms and auctions, leaving open how to design interventions for general repeated games. We address this gap by formalizing the connection between empirical observations from prior work on Q-learning collusion and classical theory of Simple Penal Codes (SPCs). We show any non-trivial SPC induces

Read original source ↗ Open in workspace

recordType

paper

region

Global