Skip to Main content Skip to Navigation
New interface
Conference papers

Learning to Identify Rush Strategies in StarCraft

Abstract : This paper examines strategies used in StarCraft II, a real-time strategy (RTS) game in which two opponents compete in a battlefield context. The RTS genre requires players to make effective strategic decisions. How players execute the selected strategies affects the game result. We propose a method to automatically classify strategies as rush or non-rush strategies using support vector machines (SVMs). We collected game replay data from an online StarCraft II community and focused on high-level players to design the proposed classifier by evaluating four feature functions: (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, (iii) the lower bound of the start time to build a second base, and (iv) the upper bound of the start time to build a specific building. By evaluating these features, we obtained the parameters combinations required to design and construct the proposed SVM-based rush identifier. Then we implemented our findings into a StarCraft: Brood War (StarCraft I) agent to demonstrate the effectiveness of the proposed method in a real-time game environment.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Tuesday, May 14, 2019 - 1:52:57 PM
Last modification on : Friday, December 10, 2021 - 2:56:30 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Teguh Budianto, Hyunwoo Oh, Takehito Utsuro. Learning to Identify Rush Strategies in StarCraft. 17th International Conference on Entertainment Computing (ICEC), Sep 2018, Poznan, Poland. pp.90-102, ⟨10.1007/978-3-319-99426-0_8⟩. ⟨hal-02128626⟩



Record views


Files downloads