Skip to Main content Skip to Navigation
Conference papers

Identifying Rush Strategies Employed in StarCraft II Using Support Vector Machines

Abstract : This paper studies the strategies used in StarCraft II, a real-time strategy game (RTS) wherein two sides fight against each other in a battlefield context. We propose an approach which automatically classifies StarCraft II game-log collections into rush and non-rush strategies using a support vector machine (SVM). To achieve this, three types of features are evaluated: (i) the upper bound of variance in time series for the numbers of workers, (ii) the upper bound of the numbers of workers at a specific time, and (iii) the lower bound of the start time for building the second base. Thus, by evaluating these features, we obtain the optimal parameters combinations.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.inria.fr/hal-01771286
Contributor : Hal Ifip <>
Submitted on : Thursday, April 19, 2018 - 2:36:35 PM
Last modification on : Tuesday, May 26, 2020 - 10:08:02 PM
Document(s) archivé(s) le : Tuesday, September 18, 2018 - 12:50:45 PM

File

978-3-319-66715-7_39_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Teguh Budianto, Hyunwoo Oh, Yi Ding, Zi Long, Takehito Utsuro. Identifying Rush Strategies Employed in StarCraft II Using Support Vector Machines. 16th International Conference on Entertainment Computing (ICEC), Sep 2017, Tsukuba City, Japan. pp.357-361, ⟨10.1007/978-3-319-66715-7_39⟩. ⟨hal-01771286⟩

Share

Metrics

Record views

117

Files downloads

39