Deep Q-Learning Market Makers in a Multi-Agent Simulated Stock Market

TL;DR

This paper explores the use of Deep Q-Learning for creating intelligent market makers in simulated stock markets, analyzing their behavior in competitive and non-competitive scenarios and the transferability of strategies.

Contribution

It introduces RL-based market maker agents and studies their performance and strategy adaptation in simulated environments, including policy transfer across different scenarios.

Findings

RL market makers are profitable in simulated markets

Agents adapt strategies effectively in competitive settings

Policy transfer impacts agent performance

Abstract

Market makers play a key role in financial markets by providing liquidity. They usually fill order books with buy and sell limit orders in order to provide traders alternative price levels to operate. This paper focuses precisely on the study of these markets makers strategies from an agent-based perspective. In particular, we propose the application of Reinforcement Learning (RL) for the creation of intelligent market markers in simulated stock markets. This research analyzes how RL market maker agents behaves in non-competitive (only one RL market maker learning at the same time) and competitive scenarios (multiple RL market markers learning at the same time), and how they adapt their strategies in a Sim2Real scope with interesting results. Furthermore, it covers the application of policy transfer between different experiments, describing the impact of competing environments on RL agents performance. RL and deep RL techniques are proven as profitable market maker approaches, leading to a better understanding of their behavior in stock markets.