Identifying Rush Strategies Employed in StarCraft II Using Support Vector Machines - Entertainment Computing – ICEC 2017
Conference Papers Year : 2017

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.
Fichier principal
Vignette du fichier
978-3-319-66715-7_39_Chapter.pdf (130.22 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01771286 , version 1 (19-04-2018)

Licence

Identifiers

Cite

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⟩
112 View
152 Download

Altmetric

Share

More