Logo PTI Logo FedCSIS

Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 43

StarCraft strategy learning refinement using replay snapshotting

,

DOI: http://dx.doi.org/10.15439/2025F2657

Citation: Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 43, pages 315–320 ()

Full text

Abstract. We propose a new replay snapshotting (RS) technique for strategy learning from past matches in real-time strategy game StarCraft: Brood War (SCBW). It allows for more precise understanding of particular strategy aspects by sampling the state of selected game features at important checkpoints during a match. We use RS to extract and refine a set of strategies from a large replay dataset STARDATA. To validate our approach in a competitive environment, we implement an AI agent for SCBW. It is able to perform the extracted strategy set against opponents in the BASIL Ladder competition. The agent consistently achieves rank C with 56 \% win rate which is a significant improvement over our previous approaches.

References

  1. Z. Lin, J. Gehring, V. Khalidov and G. Synnaeve, “STARDATA: A StarCraft AI Research Dataset,” 13th AAAI Conf. Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017, pp. 50–56, https://dx.doi.org/10.48550/arXiv.1708.02139
  2. S. Ontañon, G. Synnaeve, A. Uriarte, F. Richoux, D. Churchill and M. Preuss, “A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft,” IEEE Trans. Computational Intelligence and AI in games, IEEE Computational Intelligence Society, 2013, 5(4), pp. 293–311, https://dx.doi.org/10.1109/TCIAIG.2013.2286295
  3. Mi. Čertický, D. Churchill, K.-J. Kim, Ma. Čertický and R. Kelly, “StarCraft AI Competitions, Bots and Tournament Manager Software,” IEEE Trans. Games, 2018, 11(3), pp. 227–237, https://dx.doi.org/10.1109/TG.2018.2883499
  4. O. Vinyals, I. Babuschkin et al., “Grandmaster level in StarCraft II using multi-agent reinforcement learning,” Nature, 2019, 575, pp. 350–354, https://dx.doi.org/10.1038/s41586-019-1724-z
  5. B. G. Weber and M. Mateas, “A data mining approach to strategy prediction,” IEEE Symp. Computational Intelligence and Games, 2009, pp. 140-147, https://dx.doi.org/10.1109/CIG.2009.5286483
  6. H. C. Cho, K. J. Kim and S. B. Cho, “Replay-based strategy prediction and build order adaptation for StarCraft AI bots,” IEEE Conf. Computational Intelligence in Games (CIG), 2013, pp. 1-7, https://dx.doi.org/10.1109/CIG.2013.6633666
  7. G. Synnaeve and P. Bessière, “A Dataset for StarCraft AI & an Example of Armies Clustering,” Artificial Intelligence in Adversarial Real-Time Games, 2012,, https://dx.doi.org/10.48550/arXiv.1211.4552
  8. Š. Krištofı́k, P. Malı́k, M. Kasáš, Š. Neupauer, “StarCraft agent strategic training on a large human versus human game replay dataset,” Federated Conf. Computer Science and Information Systems, FedCSIS 2020, 21, ACSIS, pp. 391–399, https://dx.doi.org/10.15439/2020F178
  9. M. Świechowski, “Game AI Competitions: Motivation for the Imitation Game-Playing Competition,” Federated Conf. Computer Science and Information Systems, FedCSIS 2020, 21, ACSIS, pp. 155–160, https://dx.doi.org/10.15439/2020F126
  10. Š. Krištofı́k, M. Kasáš, P. Malı́k, “StarCraft strategy classification of a large human versus human game replay dataset,” Federated Conf. Computer Science and Information Systems, FedCSIS 2021, 25, ACSIS, pp. 137–140, https://dx.doi.org/10.15439/2021F48
  11. G. Robertson, I. Watson, “A Review of Real-Time Strategy Game AI,” AI Magazine, 2014, 35(4), pp. 75–104, https://dx.doi.org/10.1609/aimag.v35i4.2478
  12. S. Xu, H. Kuang et al., “Macro action selection with deep reinforcement learning in StarCraft,” 15th AAAI Conf. Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2019, pp. 94–99, https://dx.doi.org/10.48550/ARXIV.1812.00336
  13. J. J. Merelo-Guervós, A. Fernández-Ares et al., “RedDwarfData: a simplified dataset of StarCraft matches,” 2017, https://dx.doi.org/10.48550/arXiv.1712.10179
  14. F. Dai, J. Gong, J. Huang, J. Hao, “Macromanagement and Strategy Classification in Real-Time Strategy Games,” 2nd China Symp. Cognitive Computing and Hybrid Intelligence (CCHI), 2019, pp. 263–267, https://dx.doi.org/10.1109/CCHI.2019.8901957
  15. N. Justesen, S. Risi, “Learning Macromanagement in StarCraft from Replays using Deep Learning,” 2017, https://dx.doi.org/10.48550/arXiv.1707.03743
  16. C. Shi, B. Wei et al., “A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm,” J. Wireless Comm. and Networking, 2021, https://dx.doi.org/10.1186/s13638-021-01910-w
  17. N. Justensen, M. Kaselimi et at., “Human-like Bots for Tactical Shooters Using Compute-Efficient Sensors,” 2024, https://dx.doi.org/10.48550/arXiv.2501.00078
  18. J. Gehring, D. Ju, V. Mella, D. Gant, N. Usunier, G. Synnaeve, “High-Level Strategy Selection under Partial Observability in StarCraft: Brood War,” 2018, https://dx.doi.org/10.48550/arXiv.1811.08568