SCAIL: An integrated Starcraft AI system

Jay Young; Fran Smith; Christopher Atkinson; Ken Poyner; Tom Chothia

doi:10.1109/CIG.2012.6374188

SCAIL: An integrated Starcraft AI system

Jay Young^*, Fran Smith, Christopher Atkinson, Ken Poyner, Tom Chothia

^*Corresponding author for this work

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

We present the work on our integrated AI system SCAIL, which is capable of playing a full round of the Real-Time Strategy game Starcraft. Our system makes use of modern AI techniques such as particle filtering, on-line machine learning, drive-based motivation systems and artificial emotions, used to find novel structure in the dynamic playing environment, which is exploited by both high and low-level control systems. We employ a principled architecture, capable of expressing high level goal-directed behaviour. We provide an overview of our system, and a comparative evaluation against the in-game AIs of Starcraft, as well as thirteen third party systems. We go on to detail how the techniques and tools we introduce provide advantages to our system over the current state-of-the-art, resulting in improved performance when competing against those systems.

Original language	English
Title of host publication	2012 IEEE Conference on Computational Intelligence and Games, CIG 2012
Pages	438-445
Number of pages	8
DOIs	https://doi.org/10.1109/CIG.2012.6374188
Publication status	Published - 1 Dec 2012
Event	2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012 - Granada, Spain Duration: 11 Sept 2012 → 14 Sept 2012

Conference

Conference	2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012
Country/Territory	Spain
City	Granada
Period	11/09/12 → 14/09/12

ASJC Scopus subject areas

Artificial Intelligence
Computer Graphics and Computer-Aided Design
Human-Computer Interaction
Software

Access to Document

10.1109/CIG.2012.6374188

Cite this

@inproceedings{7eb5ea33560c441988cf74533def47a6,

title = "SCAIL: An integrated Starcraft AI system",

abstract = "We present the work on our integrated AI system SCAIL, which is capable of playing a full round of the Real-Time Strategy game Starcraft. Our system makes use of modern AI techniques such as particle filtering, on-line machine learning, drive-based motivation systems and artificial emotions, used to find novel structure in the dynamic playing environment, which is exploited by both high and low-level control systems. We employ a principled architecture, capable of expressing high level goal-directed behaviour. We provide an overview of our system, and a comparative evaluation against the in-game AIs of Starcraft, as well as thirteen third party systems. We go on to detail how the techniques and tools we introduce provide advantages to our system over the current state-of-the-art, resulting in improved performance when competing against those systems.",

author = "Jay Young and Fran Smith and Christopher Atkinson and Ken Poyner and Tom Chothia",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/CIG.2012.6374188",

language = "English",

isbn = "9781467311922",

pages = "438--445",

booktitle = "2012 IEEE Conference on Computational Intelligence and Games, CIG 2012",

note = "2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012 ; Conference date: 11-09-2012 Through 14-09-2012",

}

TY - GEN

T1 - SCAIL

T2 - 2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012

AU - Young, Jay

AU - Smith, Fran

AU - Atkinson, Christopher

AU - Poyner, Ken

AU - Chothia, Tom

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We present the work on our integrated AI system SCAIL, which is capable of playing a full round of the Real-Time Strategy game Starcraft. Our system makes use of modern AI techniques such as particle filtering, on-line machine learning, drive-based motivation systems and artificial emotions, used to find novel structure in the dynamic playing environment, which is exploited by both high and low-level control systems. We employ a principled architecture, capable of expressing high level goal-directed behaviour. We provide an overview of our system, and a comparative evaluation against the in-game AIs of Starcraft, as well as thirteen third party systems. We go on to detail how the techniques and tools we introduce provide advantages to our system over the current state-of-the-art, resulting in improved performance when competing against those systems.

AB - We present the work on our integrated AI system SCAIL, which is capable of playing a full round of the Real-Time Strategy game Starcraft. Our system makes use of modern AI techniques such as particle filtering, on-line machine learning, drive-based motivation systems and artificial emotions, used to find novel structure in the dynamic playing environment, which is exploited by both high and low-level control systems. We employ a principled architecture, capable of expressing high level goal-directed behaviour. We provide an overview of our system, and a comparative evaluation against the in-game AIs of Starcraft, as well as thirteen third party systems. We go on to detail how the techniques and tools we introduce provide advantages to our system over the current state-of-the-art, resulting in improved performance when competing against those systems.

UR - http://www.scopus.com/inward/record.url?scp=84871999072&partnerID=8YFLogxK

U2 - 10.1109/CIG.2012.6374188

DO - 10.1109/CIG.2012.6374188

M3 - Conference contribution

AN - SCOPUS:84871999072

SN - 9781467311922

SP - 438

EP - 445

BT - 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012

Y2 - 11 September 2012 through 14 September 2012

ER -

SCAIL: An integrated Starcraft AI system

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this