Simple Reinforcement Learning Agents: Pareto Beats Nash in an Algorithmic Game Theory Study

Loading...
Thumbnail Image
Penn collection
Operations, Information and Decisions Papers
Degree type
Discipline
Subject
Q-learning
algorithmic game theory
games
learning and games
Other Social and Behavioral Sciences
Set Theory
Theory and Algorithms
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Kimbrough, Steven. O
Lu, Ming
Contributor
Abstract

Repeated play in games by simple adaptive agents is investigated. The agents use Q-learning, a special form of reinforcement learning, to direct learning of behavioral strategies in a number of 2×2 games. The agents are able effectively to maximize the total wealth extracted. This often leads to Pareto optimal outcomes. When the rewards signals are sufficiently clear, Pareto optimal outcomes will largely be achieved. The effect can select Pareto outcomes that are not Nash equilibria and it can select Pareto optimal outcomes among Nash equilibria.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2005-03-01
Journal title
Information Systems and e-Business Management
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection