Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books
Teaching AI to make money by quoting prices in betting markets
Researchers trained artificial intelligence agents to act as market makers on prediction markets like Polymarket, where they quote buy and sell prices to earn the spread between them. The key innovation was splitting the problem into two cooperating agents—one deciding what prices to quote and another managing the risk of holding too much inventory—using a technique called cooperative multi-agent reinforcement learning. The redesigned system quoted prices more often and lost less money than baseline approaches, though none yet achieved consistent profitability on held-out test markets.
Prediction markets need market makers to function smoothly, but manually operating one is complex and risky. If AI can learn to do this profitably, it could automate liquidity provision in betting markets, making them cheaper and faster for regular users. The research also demonstrates a template for training AI agents to handle real financial data and extended time horizons, which could apply to other markets where thin trading or sparse data makes human operation difficult.