Q-learning agents in a Cournot oligopoly model

L.R. Waltman, U. Kaymak

Research output: Contribution to journalArticleProfessional

46 Citations (SciVal)


QQ-learning is a reinforcement learning model from the field of artificial intelligence. We study the use of QQ-learning for modeling the learning behavior of firms in repeated Cournot oligopoly games. Based on computer simulations, we show that QQ-learning firms generally learn to collude with each other, although full collusion usually does not emerge. We also present some analytical results. These results provide insight into the underlying mechanism that causes collusive behavior to emerge. QQ-learning is one of the few learning models available that can explain the emergence of collusive behavior in settings in which there is no punishment mechanism and no possibility for explicit communication between firms.
Original languageEnglish
Pages (from-to)3275-3293
Number of pages19
JournalJournal of Economic Dynamics and Control
Issue number10
Publication statusPublished - 2008


Dive into the research topics of 'Q-learning agents in a Cournot oligopoly model'. Together they form a unique fingerprint.

Cite this