The Economics of No-regret Learning Algorithms

2026-01-29

AI Summary

This study addresses how market and game outcomes evolve when economic agents are driven by algorithms. Moving beyond traditional rationality assumptions, the paper adopts no-regret learning as its analytical framework, systematically integrating its foundations in computer science with cutting-edge applications in economics. By synthesizing tools from game theory, statistical inference, and algorithmic game analysis, the work critically examines emerging issues such as algorithmic manipulation, collusion, and causal inference. The research uncovers novel equilibrium properties that arise from algorithmic interactions, offering both theoretical insights and analytical instruments to better understand the profound implications of algorithms for market efficiency, fairness, and regulatory design.

Technology Category

• Game Theory and Economic Paradigms: Mechanism Design
• Multiagent Systems: Mechanism Design
• Machine Learning: Causal Learning

Application Category

• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Social Networks and Social Media: Computational social science

Abstract

A fundamental challenge for modern economics is to understand what happens when actors in an economy are replaced with algorithms. Like rationality has enabled understanding of outcomes of classical economic actors, no-regret can enable the understanding of outcomes of algorithmic actors. This review article covers the classical computer science literature on no-regret algorithms to provide a foundation for an overview of the latest economics research on no-regret algorithms, focusing on the emerging topics of manipulation, statistical inference, and algorithmic collusion.

Problem

• no-regret learning
• algorithmic actors
• economic outcomes
• algorithmic collusion
• manipulation

Innovation

• no-regret learning
• algorithmic collusion
• manipulation
• statistical inference
• algorithmic economics