Q-Learning and Algorithmic Market Making: Loss-free, Collusive, or Competitive Prices?

Antonio Guarino, Philippe Jehiel and James Symons-Hicks

No 20461, CEPR Discussion Papers from Centre for Economic Policy Research

Abstract: We study whether Algorithmic Market Makers using Q-learning produce competitive or supra-competitive prices in a quote-driven asset market. We show, through simulations and analytically, that the result depends on the way the algorithm is set up. A basic Q-learning algorithm leads to loss-free prices and is, therefore, not fit for trade. Carefully choosing the exploration and learning parameters leads to less extreme prices, but still far away from the competitive ones. When we endow the algorithm with a basic understanding of the market and basic information about outstanding quotes, the Q-learning algorithms produce competitive prices.

Keywords: Algorithmic Market Making; Q-learning; Reinforcement learning; Competitive equilibrium; Artificial intelligence; Max-min (search for similar items in EconPapers)
JEL-codes: G12 G14 (search for similar items in EconPapers)
Date: 2025-07
References: Add references at CitEc
Citations:

Downloads: (external link)
https://cepr.org/publications/DP20461 (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:cpr:ceprdp:20461

Ordering information: This working paper can be ordered from
https://cepr.org/publications/DP20461

Access Statistics for this paper

More papers in CEPR Discussion Papers from Centre for Economic Policy Research 33 Great Sutton Street, London EC1V 0DX, UK.
Bibliographic data for series maintained by CEPR ().