High-level reinforcement learning in strategy games

Christopher Amato, Guy Shani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

34 Scopus citations

Abstract

Video games provide a rich testbed for artificial intelligence methods. In particular, creating automated opponents that perform well in strategy games is a difficult task. For instance, human players rapidly discover and exploit the weaknesses of hard coded strategies. To build better strategies, we suggest a reinforcement learning approach for learning a policy that switches between high-level strategies. These strategies are chosen based on different game situations and a fixed opponent strategy. Our learning agents are able to rapidly adapt to fixed opponents and improve deficiencies in the hard coded strategies, as the results demonstrate.

Original languageEnglish
Title of host publication9th International Joint Conference on Autonomous Agents and Multiagent Systems 2010, AAMAS 2010
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages75-82
Number of pages8
ISBN (Print)9781617387715
StatePublished - 1 Jan 2010
Event9th International Joint Conference on Autonomous Agents and Multiagent Systems 2010, AAMAS 2010 - Toronto, ON, Canada
Duration: 10 May 2010 → …

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume1
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Conference

Conference9th International Joint Conference on Autonomous Agents and Multiagent Systems 2010, AAMAS 2010
Country/TerritoryCanada
CityToronto, ON
Period10/05/10 → …

Keywords

  • Reinforcement Learning
  • Video games
  • Virtual agents

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'High-level reinforcement learning in strategy games'. Together they form a unique fingerprint.

Cite this