Abstract
Realtime strategy games (and especially StarCraft II) are currently becoming the ‘next big thing’ in Game AI, as building human competitive bots for complex games is still not possible. However, the abundance of existing game data makes StarCraft II an ideal testbed for machine learning. We attempt to use this for establishing winner predictors that in strong contrast to existing methods rely on partial information available to one player only. Such predictors can be made available to human players as a supportive AI component, but they can more importantly be used as state evaluations in order to inform strategic planning for a bot. We show that it is actually possible to reach accuracies near to the ones reported for full information with relatively simple techniques. Next to performance, we also look at the interpretability of the models that may be valuable for supporting human players as well as bot creators.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Duygu Cakmak: The grand strategy approach to AI at Emotech Meet AI 9 (London), March 22nd 2018.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
References
Alburg, H., et al.: Making and Acting on Predictions in StarCraft: Brood War. University of Gothenburg (2014)
Álvarez-Caballero, A., et al.: Early prediction of the winner in StarCraft matches. In: International Joint Conference on Computational Intelligence (2017)
Avontuur, T., Spronck, P., van Zaanen, M.: Player skill modeling in Starcraft II. In: Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Boston, MA, USA, pp. 2–8. AAAI Press (2014)
Breiman, L., et al.: Classiffication and Regression Trees. Wadsworth and Brooks, Monterey (1984)
Browder, D.: The game design of STARCRAFT II: designing an E-Sport. In: Game Developers Conference (GDC) (2011). http://www.gdcvault.com/play/1014488/The-Game-Design-of-STARCRAFT
Browne, C., Maire, F.: Evolutionary game design. IEEE Trans. Comput. Intell. AI Games 2(1), 1–16 (2010)
Browne, C.B., et al.: A survey of monte carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1–43 (2012)
Erickson, G., Buro, M.: Global state evaluation in StarCraft. In: AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, pp. 112–118 (2014)
Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning Workshop (2014). https://arxiv.org/abs/1503.02531
Kovarsky, A., Buro, M.: Heuristic search applied to abstract combat games. In: Kégl, B., Lapalme, G. (eds.) AI 2005. LNCS (LNAI), vol. 3501, pp. 66–78. Springer, Heidelberg (2005). https://doi.org/10.1007/11424918_9
Lopes, R., Bidarra, R.: Adaptivity challenges in games and simulations: a survey. IEEE Trans. Comput. Intell. AI Games 3(2), 85–99 (2011)
Miller, G.: The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychol. Rev. 63, 81–97 (1956)
Olah, C., et al.: The building blocks of interpretability. Distill (2018). https://distill.pub/2018/building-blocks
Perez-Liebana, D., et al.: General video game AI: competition, challenges and opportunities. In: AAAI Conference on Artificial Intelligence, pp. 4335–4337 (2016)
Ravari, Y.N., Bakkes, S., Spronck, P.: StarCraft winner prediction. In: AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2016)
Robertson, G., Watson, I.D.: An improved dataset and extraction process for Starcraft AI. In: FLAIRS Conference, pp. 255–260 (2014)
Sánchez-Ruiz-Granados, A.A.: Predicting the winner in two player StarCraft games. In: CoSECivi, pp. 24–35 (2015)
Stanescu, M., et al.: Evaluating real-time strategy game states using convolutional neural networks. In: IEEE Conference on Computational Intelligence and Games (2016)
Stanescu, M., et al.: Predicting army combat outcomes in StarCraft. In: AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, pp. 86–92 (2013)
Summerville, A., et al.: Understanding mario: an evaluation of design metrics for platformers. In: Foundations of Digital Games. ACM, New York (2017)
Čertický, M., Churchill, D.: The current state of StarCraft AI competitions and bots. In: Artificial Intelligence and Interactive Digital Entertainment Conference (2017)
Vinyals, O., et al.: StarCraft II: A New Challenge for Reinforcement Learning. CoRR abs/1708.04782 (2017). arXiv: 1708.04782
Yang, P., Harrison, B.E., Roberts, D.L.: Identifying patterns in combat that are predictive of success in MOBA games. In: Foundations of Digital Games (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Volz, V., Preuss, M., Bonde, M.K. (2019). Towards Embodied StarCraft II Winner Prediction. In: Cazenave, T., Saffidine, A., Sturtevant, N. (eds) Computer Games. CGW 2018. Communications in Computer and Information Science, vol 1017. Springer, Cham. https://doi.org/10.1007/978-3-030-24337-1_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-24337-1_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24336-4
Online ISBN: 978-3-030-24337-1
eBook Packages: Computer ScienceComputer Science (R0)