Metraipolis › archive › dc_46dc4bc7f0bb
Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books — arXiv:2610.26789
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.26789
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-20T17:34:33.257Z
- SHA-256 of the archived text
bce97e36023d6643b2bcd8fb9b0ad7cd75e8abc48d9758b78283029702fad3d2- Stable URL of this page
https://metraipolis.com/documento/dc_46dc4bc7f0bb
How to cite
Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books — arXiv:2610.26789 — arXiv (en), https://arxiv.org/abs/2610.26789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46dc4bc7f0bb (Metraipolis archive dc_46dc4bc7f0bb, sha256 bce97e36023d6643b2bcd8fb9b0ad7cd75e8abc48d9758b78283029702fad3d2)
BibTeX
@misc{dc46dc4bc7f0bb,
title = {Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books — arXiv:2610.26789},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.26789},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46dc4bc7f0bb; sha256 bce97e36023d6643b2bcd8fb9b0ad7cd75e8abc48d9758b78283029702fad3d2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A market maker provides liquidity by quoting prices to buy and sell an asset, earning the spread while managing inventory risk. We study market makers trained with multi-agent reinforcement learning on prediction markets, specifically Polymarket, whose thin order books pose distinct challenges. Three challenges underpin this research: adverse selection may cause a policy trained on real data to stop quoting; the consequences of a quote can arrive many steps after the action; and prediction-market L2 data does not identify individual orders needed for simulation. We address these challenges by reconstructing order-level LOBSTER-format data from Polymarket and training agents in JaxMARL-HFT on 417 real markets. We enrich the baseline market maker's observation space with the book and recent flow, redesign its actions and inventory controls, and propose a cooperative multi-agent decomposition into a quoter and a risk manager trained using recurrent Independent Proximal Policy Optimisation (IPPO) with RNN policies. We investigate reward shaping, particularly reward blending and post-fill markout, to mitigate credit-assignment difficulties between the agents. Our redesigned single-agent market maker quotes more frequently and incurs smaller held-out losses than the retrained JaxMARL-HFT baseline, although the contributions of jointly changed observations, actions and risk constraints are not separately identified. Decomposition alone performs poorly; careful reward design substantially improves the desk relative to the unshaped split and yields our best result. Models are evaluated on realised end-of-episode portfolio value on held-out markets. None establishes positive average portfolio value in periodic held-out evaluation, and each configuration was trained with one seed. The environment, data and protocol lay a foundation for makers that quote many linked markets at once. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA); Trading and Market Microstructure (q-fin.TR). Pagina del lavoro: https://arxiv.org/abs/2610.26789 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-20T17:34:32.004Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).