arXiv cs.MA· Daniele Montagnani, Andrea Coletta, Antonietta Mira, Aldo Glielmo·· 13 小时前AI 评分31
JaxMARL-BC：秒级训练宏观经济多智能体强化学习模型
JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds
AI 导读
JaxMARL-BC 是 JAX 加速的宏观经济多智能体强化学习模拟器，训练 MARL-BC 经济模型仅需数秒，比参考实现快 75x 至 724x，并可扩展至 200,000 个独立学习家庭。该工作验证了其与经典 DSGE 模型极限的一致性，并通过对异质资本回报扩展模型的概念验证校准展示了实用价值——原本需一个多月的实验缩短至两小时。JaxMARL-BC 已开源发布。
正文 · 原文
Abstract:Multi-agent reinforcement learning (MARL) offers a principled way of populating simulated economies with many heterogeneous decision makers. Its adoption, pioneered in finance, has nonetheless been slow in macroeconomics because of two main limitations: the lack of a shared frame of reference connecting MARL systems to dynamic stochastic general equilibrium (DSGE) models the profession already trusts, and the very long training times. The first limitation was recently addressed by the Multi-Agent Reinforcement Learning Business Cycle (MARL-BC), which places deep RL households in a real business cycle economy and reduces to classic DSGE models in specific limits. Here we address the second limitation. We present JaxMARL-BC, a JAX-accelerated simulator that trains MARL-BC economies in seconds (between 75x and 724x faster than the reference implementation), and scales to 200,000 independent learning households. We verify its correctness against the known DSGE limits, characterise its scaling through a simple cost law, and demonstrate its value by a proof-of-concept calibration of an extended model with heterogeneous returns on capital, in a two-hour experiment that would previously have taken over a month. We release JaxMARL-BC as open source.
| Comments: | 9 pages, 7 figures |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); General Economics (econ.GN) |
| ACM classes: | I.2.11; I.2.6; J.4; I.6.8 |
| Cite as: | arXiv:2610.28907 [cs.MA] |
| (or arXiv:2610.28907v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28907 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the 7th ACM International Conference on AI in Finance (ICAIF '26), Milan, Italy, 2026 |
Submission history
From: Aldo Glielmo Dr. [view email]
[v1]
Tue, 20 Oct 2026 20:35:44 UTC (3,445 KB)
来源：arXiv cs.MA · arxiv.org