ABIDES-Economist: Agent-Based Simulation of Economic Systems with Learning Agents

2024-02-14

arXiv.org

AI Summary

This paper addresses the challenge of building a verifiable, heterogeneous-agent macroeconomic simulation platform. Methodologically, it designs a multi-agent system integrating heterogeneous households, firms, a central bank, and the government; supports both rule-based and reinforcement learning (RL) policies—specifically PPO and SAC—and pioneers the integration of the OpenAI Gym interface into macroeconomic simulation. Micro-level behavioral calibration is coupled with macro-level dynamics to enable exogenous shock modeling and counterfactual causal analysis grounded in real U.S. economic data. Contributions include: (1) the first systematic integration of deep RL into a general-purpose macroeconomic simulation framework; (2) empirical validation across two canonical scenarios—adaptive learning of employment preferences among skill-heterogeneous households, and evolutionary pricing responses of firms following a firm-specific productivity shock—demonstrating that learning agents substantially reshape equilibrium trajectories; and (3) an open-source, reproducible, and extensible simulation infrastructure.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

We introduce a multi-agent simulator for economic systems comprised of heterogeneous Households, heterogeneous Firms, Central Bank and Government agents, that could be subjected to exogenous, stochastic shocks. The interaction between agents defines the production and consumption of goods in the economy alongside the flow of money. Each agent can be designed to act according to fixed, rule-based strategies or learn their strategies using interactions with others in the simulator. We ground our simulator by choosing agent heterogeneity parameters based on economic literature, while designing their action spaces in accordance with real data in the United States. Our simulator facilitates the use of reinforcement learning strategies for the agents via an OpenAI Gym style environment definition for the economic system. We demonstrate the utility of our simulator by simulating and analyzing two hypothetical (yet interesting) economic scenarios. The first scenario investigates the impact of heterogeneous household skills on their learned preferences to work at different firms. The second scenario examines the impact of a positive production shock to one of two firms on its pricing strategy in comparison to the second firm. We aspire that our platform sets a stage for subsequent research at the intersection of artificial intelligence and economics.

Problem

• Simulating economic systems with learning agents
• Calibrating heterogeneous agent-based economic models
• Designing regulatory policies using validated simulation

Innovation

• Agent-based simulator with reinforcement learning
• OpenAI Gym for multi-agent learning
• Calibration using economic data and stylized facts