Feature Extraction for StarCraft II League Prediction †
Abstract
:1. Introduction
2. Related Work
3. Methodology
3.1. Data Collection
3.2. Evaluation
4. Results
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Lee, C.; Ahn, C.W. Extracting Control Features to Predict a Player’s League in StarCraft II; SMA: Jeju, Korea, 2020. [Google Scholar]
- Palero, F.; Ramirez-Atencia, C.; Camacho, D. Online Gamers Classification Using K-Means. In Intelligent Distributed Computing VIII; Springer: Berlin/Heidelberg, Germany, 2015; pp. 201–208. [Google Scholar]
- Vicencio-Moreira, R.; Mandryk, R.L.; Gutwin, C. Now You Can Compete With Anyone: Balancing Players of Different Skill Levels in a First-Person Shooter Game. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI’15, Seoul, Korea, 18–23 April 2015; pp. 2255–2264. [Google Scholar] [CrossRef]
- Sarkar, A.; Cooper, S. Level difficulty and player skill prediction in human computation games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Snowbird, UT, USA, 5–9 October 2017; Volume 13. [Google Scholar]
- Justesen, N.; Risi, S. Learning macromanagement in starcraft from replays using deep learning. In Proceedings of the 2017 IEEE Conference on Computational Intelligence and Games (CIG), New York, NY, USA, 22–25 August 2017; pp. 162–169. [Google Scholar]
- Avontuur, T.; Spronck, P.; Van Zaanen, M. Player skill modeling in Starcraft II. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 2013, Boston, MA, USA, 14–18 October 2013. [Google Scholar]
- Lin, Z.; Gehring, J.; Khalidov, V.; Synnaeve, G. Stardata: A starcraft ai research dataset. arXiv 2017, arXiv:1708.02139. [Google Scholar]
- Robertson, G.; Watson, I. An improved dataset and extraction process for starcraft ai. In Proceedings of the The Twenty-Seventh International Flairs Conference, Pensacola Beach, FL, USA, 21–23 May 2014. [Google Scholar]
- Synnaeve, G.; Bessiere, P. A Dataset for StarCraft AI & an Example of Armies Clustering. arXiv 2012, arXiv:1211.4552. [Google Scholar]
- Synnaeve, G.; Bessiere, P. A Bayesian model for opening prediction in RTS games with application to StarCraft. In Proceedings of the 2011 IEEE Conference on Computational Intelligence and Games (CIG’11), Seoul, Korea, 31 August–3 September 2011; pp. 281–288. [Google Scholar]
- Hsieh, J.L.; Sun, C.T. Building a player strategy model by analyzing replays of real-time strategy games. In Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China, 1–8 June 2008; pp. 3106–3111. [Google Scholar]
- Schadd, F.; Bakkes, S.; Spronck, P. Opponent Modeling in Real-Time Strategy Games. In GAMEON; Citeseer: University Park, PA, USA, 2007; pp. 61–70. [Google Scholar]
- Weber, B.G.; Mateas, M. A data mining approach to strategy prediction. In Proceedings of the 2009 IEEE Symposium on Computational Intelligence and Games, Milan, Italy, 7–10 September 2009; pp. 140–147. [Google Scholar] [CrossRef]
- Ravari, Y.N.; Bakkes, S.; Spronck, P. Starcraft winner prediction. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Burlingame, CA, USA, 8–12 October 2016; Volume 12. [Google Scholar]
- Stanescu, M.; Hernandez, S.P.; Erickson, G.; Greiner, R.; Buro, M. Predicting army combat outcomes in StarCraft. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Boston, MA USA, 14–18 October 2013; Volume 9. [Google Scholar]
- Liu, S.; Ballinger, C.; Louis, S.J. Player identification from RTS game replays. In Proceedings of the 28th CATA, Honolulu, HI, USA, 4–6 March 2013; pp. 313–317. [Google Scholar]
- Chen, Y.; Aitchison, M.; Sweetser, P. Improving StarCraft II Player League Prediction with Macro-Level Features. In Proceedings of the Australasian Joint Conference on Artificial Intelligence, Canberra, Australia, 29–30 November 2020; pp. 256–268. [Google Scholar]
- Thompson, J.J.; Blair, M.R.; Chen, L.; Henrey, A.J. Video game telemetry as a critical tool in the study of complex skill learning. PLoS ONE 2013, 8, e75129. [Google Scholar] [CrossRef] [PubMed]
- Vinyals, O.; Babuschkin, I.; Czarnecki, W.M.; Mathieu, M.; Dudzik, A.; Chung, J.; Choi, D.H.; Powell, R.; Ewalds, T.; Georgiev, P.; et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 2019, 575, 350–354. [Google Scholar] [CrossRef] [PubMed]
- Ballinger, C.; Liu, S.; Louis, S.J. Identifying Players and Predicting Actions from RTS Game Replays. In Proceedings of the 28th International Conference on Computer Applications in Industry and Engineering, San Diego, CA, USA, 12–14 October 2015. [Google Scholar]
- Zhang, S.; Li, X.; Zong, M.; Zhu, X.; Cheng, D. Learning k for knn classification. ACM Trans. Intell. Syst. Technol. 2017, 8, 43. [Google Scholar] [CrossRef] [Green Version]
League | Bronze | Silver | Gold | Platinum | Diamond | Master | Grandmaster |
---|---|---|---|---|---|---|---|
Number | 1078 | 4651 | 6813 | 6380 | 40,607 | 13,467 | 9884 |
Dataset | Description |
---|---|
D1 | Combat |
D2 | 18 s after the game starts |
D3 | 18 s before the game is over |
D4 | 5 min after the game starts |
D5 | 5 min before the game is over |
D6 | Entire game |
D1 | D2 | D3 | D4 | D5 | D6 | ||
---|---|---|---|---|---|---|---|
k-NN | Accuracy | 0.62 | 0.62 | 0.64 | 0.71 | 0.71 | 0.73 |
Precision | 0.67 | 0.63 | 0.69 | 0.75 | 0.75 | 0.76 | |
Recall | 0.59 | 0.58 | 0.62 | 0.68 | 0.68 | 0.70 | |
F1-score | 0.63 | 0.61 | 0.65 | 0.72 | 0.72 | 0.73 | |
Random Forest | Accuracy | 0.63 | 0.64 | 0.62 | 0.72 | 0.73 | 0.75 |
Precision | 0.64 | 0.64 | 0.67 | 0.77 | 0.76 | 0.78 | |
Recall | 0.59 | 0.59 | 0.62 | 0.72 | 0.70 | 0.73 | |
F1-score | 0.62 | 0.62 | 0.64 | 0.75 | 0.73 | 0.75 |
D1 + D2 + D3 | D4 + D5 + D6 | ||||||||
---|---|---|---|---|---|---|---|---|---|
Accuracy | Precision | Recall | F1-Score | Accuracy | Precision | Recall | F1-Score | ||
k-NN | Bronze | 0.64 | 0.66 | 0.47 | 0.55 | 0.77 | 0.91 | 0.62 | 0.74 |
Silver | 0.61 | 0.57 | 0.59 | 0.76 | 0.78 | 0.77 | |||
Gold | 0.60 | 0.62 | 0.61 | 0.75 | 0.77 | 0.76 | |||
Platinum | 0.68 | 0.59 | 0.63 | 0.78 | 0.72 | 0.75 | |||
Diamond | 0.58 | 0.68 | 0.63 | 0.74 | 0.82 | 0.78 | |||
Master | 0.66 | 0.74 | 0.70 | 0.77 | 0.82 | 0.79 | |||
Grandmaster | 0.75 | 0.58 | 0.65 | 0.85 | 0.70 | 0.77 | |||
Random Forest | Bronze | 0.64 | 0.67 | 0.46 | 0.55 | 0.77 | 0.91 | 0.64 | 0.75 |
Silver | 0.61 | 0.57 | 0.59 | 0.76 | 0.78 | 0.77 | |||
Gold | 0.60 | 0.61 | 0.60 | 0.76 | 0.77 | 0.76 | |||
Platinum | 0.68 | 0.58 | 0.63 | 0.78 | 0.71 | 0.74 | |||
Diamond | 0.58 | 0.67 | 0.62 | 0.73 | 0.82 | 0.77 | |||
Master | 0.66 | 0.74 | 0.70 | 0.77 | 0.82 | 0.79 | |||
Grandmaster | 0.75 | 0.58 | 0.65 | 0.85 | 0.71 | 0.77 |
k-NN | Random Forest | |||||||
---|---|---|---|---|---|---|---|---|
Accuracy | Precision | Recall | F1-Score | Accuracy | Precision | Recall | F1-Score | |
Bronze | 0.73 | 0.96 | 0.53 | 0.68 | 0.75 | 0.90 | 0.63 | 0.74 |
Silver | 0.68 | 0.75 | 0.71 | 0.73 | 0.77 | 0.75 | ||
Gold | 0.68 | 0.75 | 0.71 | 0.74 | 0.75 | 0.74 | ||
Platinum | 0.73 | 0.69 | 0.71 | 0.75 | 0.71 | 0.73 | ||
Diamond | 0.71 | 0.75 | 0.73 | 0.72 | 0.79 | 0.76 | ||
Master | 0.75 | 0.79 | 0.77 | 0.75 | 0.81 | 0.78 | ||
Grandmaster | 0.82 | 0.66 | 0.73 | 0.83 | 0.68 | 0.75 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lee, C.M.; Ahn, C.W. Feature Extraction for StarCraft II League Prediction. Electronics 2021, 10, 909. https://doi.org/10.3390/electronics10080909
Lee CM, Ahn CW. Feature Extraction for StarCraft II League Prediction. Electronics. 2021; 10(8):909. https://doi.org/10.3390/electronics10080909
Chicago/Turabian StyleLee, Chan Min, and Chang Wook Ahn. 2021. "Feature Extraction for StarCraft II League Prediction" Electronics 10, no. 8: 909. https://doi.org/10.3390/electronics10080909
APA StyleLee, C. M., & Ahn, C. W. (2021). Feature Extraction for StarCraft II League Prediction. Electronics, 10(8), 909. https://doi.org/10.3390/electronics10080909