Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma

Quentin Bertrand; Juan Agustin Duque; Emilio Calvano; Gauthier Gidel

2025 ICML ICML 2025

Self-Play Q-Learners Can Provably Collude in the Iterated Prisoner’s Dilemma

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Quentin Bertrand, Juan Agustin Duque, Emilio Calvano, Gauthier Gidel

Topics

Artificial Intelligence > Core AI > Agent Systems Machine Learning > Optimization & Theory > Learning Theory

Keywords

self-play iterated prisoner's dilemma collusion cooperative pavlov q-learners

Download PDF