Multi-agent reinforcement learning speeds up macroeconomic simulations immensely
JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds
Multiagent SystemsArtificial IntelligenceMachine Learning
Summary
Simulating economies with many different decision makers usually takes a very long time, which slows research in economics. The authors built a faster computer program called JaxMARL-BC that runs these simulations up to 700 times quicker and can handle vast numbers of simulated households. Their program connects advanced machine learning techniques with trusted economic models to ensure reliable results. This speed-up makes it possible to explore complex economic questions much faster than before.
What this means in practice
- •For economic modelers: Run large-scale macroeconomic simulations with many independent agents in seconds instead of weeks to improve model exploration and calibration speed.
- •For financial analysts: Use faster multi-agent simulations linked to economic theory for more detailed and timely stress tests and scenario analyses.
Authors
Daniele Montagnani, Andrea Coletta, Antonietta Mira, Aldo Glielmo
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.