Learning Nested Agent Models in an Information Economy

TL;DR

This paper explores how agents in an economic multi-agent system can decide when to model other agents strategically or act as price-takers, using a framework for incremental modeling and simulation results.

Contribution

It introduces a framework for incremental implementation of agent modeling capabilities and analyzes their impact in simulated economic populations.

Findings

Savvy buyers can avoid being cheated by sellers.

Price volatility helps predict benefits of deeper agent models.

Agent population types influence overall system behavior.

Abstract

We present our approach to the problem of how an agent, within an economic Multi-Agent System, can determine when it should behave strategically (i.e. learn and use models of other agents), and when it should act as a simple price-taker. We provide a framework for the incremental implementation of modeling capabilities in agents, and a description of the forms of knowledge required. The agents were implemented and different populations simulated in order to learn more about their behavior and the merits of using and learning agent models. Our results show, among other lessons, how savvy buyers can avoid being ``cheated'' by sellers, how price volatility can be used to quantitatively predict the benefits of deeper models, and how specific types of agent populations influence system behavior.