Online evolution for multi-action adversarial games

Niels Orsleff Justesen, Tobias Mahlmann, Julian Togelius

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Abstract

We present Online Evolution, a novel method for playing turn-based multi-action adversarial games. Such games, which include most strategy games, have extremely high branching factors due to each turn having multiple actions. In Online Evolution, an evolutionary algorithm is used to evolve the combination of atomic actions that make up a single move, with a state evaluation function used for fitness. We implement Online Evolution for the turn-based multi-action game Hero Academy and compare it with a standard Monte Carlo Tree Search implementation as well as two types of greedy algorithms. Online Evolution is shown to outperform these methods by a large margin. This shows that evolutionary planning on the level of a single move can be very effective for this sort of problems.
Original languageEnglish
Title of host publicationApplications of Evolutionary Computation : 19th European Conference, EvoApplications 2016 Porto, Portugal, March 30 – April 1, 2016 Proceedings, Part I
PublisherSpringer Publishing Company
Publication date15 Mar 2016
Pages590-603
ISBN (Electronic)978-3-319-31204-0
DOIs
Publication statusPublished - 15 Mar 2016
SeriesLecture Notes in Computer Science
Volume9597
ISSN0302-9743

Keywords

  • Online Evolution
  • Turn-based multi-action games
  • Evolutionary algorithm
  • State evaluation function
  • Hero Academy

Fingerprint

Dive into the research topics of 'Online evolution for multi-action adversarial games'. Together they form a unique fingerprint.

Cite this