Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulations

TL;DR

This paper introduces a novel approach using pre-trained Large Language Models as efficient policymakers in complex economic simulation environments, significantly improving over existing reinforcement learning methods.

Contribution

It proposes leveraging pre-trained LLMs for social decision-making in MARL, addressing sample inefficiency and flexibility issues of prior RL-based approaches.

Findings

LLMs outperform existing methods in three economic simulation environments.

Significant efficiency gains demonstrated over traditional RL approaches.

Code for the method is publicly available.

Abstract

The improvement of economic policymaking presents an opportunity for broad societal benefit, a notion that has inspired research towards AI-driven policymaking tools. AI policymaking holds the potential to surpass human performance through the ability to process data quickly at scale. However, existing RL-based methods exhibit sample inefficiency, and are further limited by an inability to flexibly incorporate nuanced information into their decision-making processes. Thus, we propose a novel method in which we instead utilize pre-trained Large Language Models (LLMs), as sample-efficient policymakers in socially complex multi-agent reinforcement learning (MARL) scenarios. We demonstrate significant efficiency gains, outperforming existing methods across three environments. Our code is available at https://github.com/hegasz/large-legislative-models.