EconoJax: A Fast & Scalable Economic Simulation in Jax

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ponse, Koen, Plaat, Aske, van Stein, Niki, Moerland, Thomas M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910949063000064
author Ponse, Koen
Plaat, Aske
van Stein, Niki
Moerland, Thomas M.
author_facet Ponse, Koen
Plaat, Aske
van Stein, Niki
Moerland, Thomas M.
contents Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in multi-agent economic environments can be slow. This paper introduces EconoJax, a fast simulated economy, based on the AI economist. EconoJax, and its training pipeline, are completely written in JAX. This allows EconoJax to scale to large population sizes and perform large experiments, while keeping training times within minutes. Through experiments with populations of 100 agents, we show how real-world economic behavior emerges through training within 15 minutes, in contrast to previous work that required several days. We additionally perform experiments in varying sized action spaces to test if some multi-agent methods produce more diverse behavior compared to others. Here, our findings indicate no notable differences in produced behavior with different methods as is sometimes suggested in earlier works. To aid further research, we open-source EconoJax on Github.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22165
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EconoJax: A Fast & Scalable Economic Simulation in Jax
Ponse, Koen
Plaat, Aske
van Stein, Niki
Moerland, Thomas M.
Multiagent Systems
Machine Learning
General Economics
Economics
Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in multi-agent economic environments can be slow. This paper introduces EconoJax, a fast simulated economy, based on the AI economist. EconoJax, and its training pipeline, are completely written in JAX. This allows EconoJax to scale to large population sizes and perform large experiments, while keeping training times within minutes. Through experiments with populations of 100 agents, we show how real-world economic behavior emerges through training within 15 minutes, in contrast to previous work that required several days. We additionally perform experiments in varying sized action spaces to test if some multi-agent methods produce more diverse behavior compared to others. Here, our findings indicate no notable differences in produced behavior with different methods as is sometimes suggested in earlier works. To aid further research, we open-source EconoJax on Github.
title EconoJax: A Fast & Scalable Economic Simulation in Jax
topic Multiagent Systems
Machine Learning
General Economics
Economics
url https://arxiv.org/abs/2410.22165