Metraipolis › archive › dc_0434fba5142f
JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds — arXiv:2610.28907
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28907
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-22T02:56:24.851Z
- SHA-256 of the archived text
da173cf4573bcf2ee10a80d5197afb519e6be306da865bca22ad4fc212294fd0- Stable URL of this page
https://metraipolis.com/documento/dc_0434fba5142f
How to cite
JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds — arXiv:2610.28907 — arXiv (en), https://arxiv.org/abs/2610.28907 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0434fba5142f (Metraipolis archive dc_0434fba5142f, sha256 da173cf4573bcf2ee10a80d5197afb519e6be306da865bca22ad4fc212294fd0)
BibTeX
@misc{dc0434fba5142f,
title = {JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds — arXiv:2610.28907},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28907},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0434fba5142f; sha256 da173cf4573bcf2ee10a80d5197afb519e6be306da865bca22ad4fc212294fd0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28907. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); General Economics (econ.GN). Pagina del lavoro: https://arxiv.org/abs/2610.28907 — 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 2026-10-22T02:56:24.505Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).