Algorithmic collusion with endogenous exploration

Ivan Conjeaud

Papers from arXiv.org

Abstract: I study a two-stage model in which two players simultaneously choose an exploration parameter for their Q-learning algorithms, which then repeatedly play a one-shot game chosen from a class of social dilemmas including the prisoner's dilemma, first and second-price auctions as well as Bertrand competition with horizontally differentiated products. The players collect the limit average payoffs obtained by their algorithms. I show that all equilibria are collusive: both players receive payoffs that are strictly higher than the payoffs received in the unique strict Nash equilibrium of the one-shot game. I then use extensive numerical simulations in a Bertrand duopoly and a parameterized prisoner's dilemma. Their results allow to gain insight on (i) the mechanism causing algorithmic collusion and (ii) the strategic role of exploration levels in the game. They reveal that in equilibrium, the players tend to choose algorithms that \textit{over-explore}, which comes at the detriment of joint payoff. These findings have important implications for algorithmic collusion.

Date: 2023-12, Revised 2026-08
New Economics Papers: this item is included in nep-cmp, nep-gth and nep-mic
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://arxiv.org/pdf/2312.02644 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2312.02644

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().