Research on cooperative multi-agent reinforcement learning for market making in prediction market order books

The study addresses market-making challenges in Polymarket's thin order books, using the JaxMARL-HFT framework to train cooperative multi-agent market-making models on 417 real markets. The market-making agents are split into quoters and risk managers, trained using recurrent independent proximal policy optimization (IPPO) combined with RNN policies. Testing showed that the improved single-agent market-making model quoted more frequently and had smaller out-of-sample losses, but none of the models achieved positive average portfolio value in out-of-sample evaluation, with only single-seed training completed.