Article
In-game action list segmentation and labeling in real-time strategy games
2012 IEEE Conference on Computational Intelligence and Games CIG : 11-14 September 2012, Granada, Spain: Proceedings
Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
9-2012
Abstract
In-game actions of real-time strategy (RTS) games are extremely useful in determining the players' strategies, analyzing their behaviors and recommending ways to improve their play skills. Unfortunately, unstructured sequences of in-game actions are hardly informative enough for these analyses. The inconsistency we observed in human annotation of in-game data makes the analytical task even more challenging. In this paper, we propose an integrated system for in-game action segmentation and semantic label assignment based on a Conditional Random Fields (CRFs) model with essential features extracted from the in-game actions. Our experiments demonstrate that the accuracy of our solution can be as high as 98.9%.
Keywords
- Computer games,
- Feature extraction,
- Conditional random fields,
- Feature extraction,
- Human annotation,
- In-game action list segmentation,
- Real-time strategy games,
- Semantic label assignment
Discipline
ISBN
9781467311946
Identifier
10.1109/CIG.2012.6374150
Publisher
IEEE
City or Country
Piscataway, NJ
Copyright Owner and License
LARC
Creative Commons License
Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International
Additional URL
http://doi.org/10.1109/CIG.2012.6374150
Citation Information
Wei GONG, Ee-Peng LIM, Palakorn ACHANANUPARP, Feida ZHU, et al.. "In-game action list segmentation and labeling in real-time strategy games" 2012 IEEE Conference on Computational Intelligence and Games CIG : 11-14 September 2012, Granada, Spain: Proceedings (2012) p. 147 - 154 Available at: http://works.bepress.com/david_lo/278/
Data set available at http://ink.library.smu.edu.sg/data/1/