DRE-Bot: A hierarchical first person shooter bot using multiple Sarsa(λ) reinforcement learners

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

8 Citations (Scopus)

Abstract

This paper describes an architecture for controlling non-player characters (NPC) in the First Person Shooter (FPS) game Unreal Tournament 2004. Specifically, the DRE-Bot architecture is made up of three reinforcement learners, Danger, Replenish and Explore, which use the tabular Sarsa(λ) algorithm. This algorithm enables the NPC to learn through trial and error building up experience over time in an approach inspired by human learning. Experimentation is carried to measure the performance of DRE-Bot when competing against fixed strategy bots that ship with the game. The discount parameter, γ, and the trace parameter, λ, are also varied to see if their values have an effect on the performance.

Original languageEnglish
Title of host publicationProceedings of CGAMES'2012 USA - 17th International Conference on Computer Games
Subtitle of host publicationAI, Animation, Mobile, Interactive Multimedia, Educational and Serious Games
Pages148-152
Number of pages5
DOIs
Publication statusPublished - 2012
Event17th International Conference on Computer Games, CGAMES 2012 - Louisville, KY, United States
Duration: 30 Jul 20121 Aug 2012

Publication series

NameProceedings of CGAMES'2012 USA - 17th International Conference on Computer Games: AI, Animation, Mobile, Interactive Multimedia, Educational and Serious Games

Conference

Conference17th International Conference on Computer Games, CGAMES 2012
Country/TerritoryUnited States
CityLouisville, KY
Period30/07/121/08/12

Keywords

  • First Person Shooter
  • Reinforcement Learning

Fingerprint

Dive into the research topics of 'DRE-Bot: A hierarchical first person shooter bot using multiple Sarsa(λ) reinforcement learners'. Together they form a unique fingerprint.

Cite this