---
title: "Learning against opponents with bounded memory"
authors:
  - "Rob Powers"
  - "Yoav Shoham"
doi: ""
url: "https://ijcai.org/proceedings/2005/167"
pdf: "https://ijcai.org/proceedings/2005/0167.pdf"
venue: "Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence"
year: 2005
pages: "817-821"
track: ""
keywords:
---

# Learning against opponents with bounded memory

Rob Powers, Yoav Shoham

*Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence*, pages 817-821.

## Abstract

Recently, a number of authors have proposed criteria for evaluating learning algorithms in multiagent systems. While well-justified, each of these has generally given little attention to one of the main challenges of a multi-agent setting: the capability of the other agents to adapt and learn as well. We propose extending existing criteria to apply to a class of adaptive opponents with bounded memory. We then show an algorithm that provably achieves an ǫ-best response against this richer class of opponents while simultaneously guaranteeing a minimum payoff against any opponent and performing well in self-play. This new algorithm also demonstrates strong performance in empirical tests against a variety of opponents in a wide range of environments.