Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 21

Proceedings of the 2020 Federated Conference on Computer Science and Information Systems

StarCraft agent strategic training on a large human versus human game replay dataset

, , ,

DOI: http://dx.doi.org/10.15439/2020F178

Citation: Proceedings of the 2020 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 21, pages 391399 ()

Full text

Abstract. Real-time strategy games are currently very popular as a testbed for AI research and education. StarCraft: Brood War (SC:BW) is one of such games. Recently, a new large, unlabeled human versus human SC:BW game replay dataset called STARDATA was published. This paper aims to prove that the player strategy diversity requirement of the dataset is met, i.e., that the diversity of player strategies in STARDATA replays is of sufficient quality. To this end, we built a competitive SC:BW agent from scratch and trained its strategic decision making process on STARDATA. The results show that in the current state of the competitive environment the agent is capable of keeping a stable rating and a decent win rate over a longer period of time. It also performs better than our other, simple rule-based agent. Therefore, we conclude that the strategy diversity requirement of STARDATA is met.


  1. M. Buro, “Real-time strategy games: A new ai research challenge,” International Joint Conferences on Artificial Intelligence, IJCAI 2003, pp. 1534-1535.
  2. Z. Lin, J. Gehring, V. Khalidov and G. Synnaeve, “STARDATA: A StarCraft AI Research Dataset,” 13th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2017, pp. 50–56, https://arxiv.org/abs/1708.02139.
  3. 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 Transactions on Computational Intelligence and AI in games, IEEE Computational Intelligence Society, 2013, 5(4), pp. 1–19, http://dx.doi.org/10.1109/TCIAIG.2013.2286295.
  4. Mi. Čertický, D. Churchill, K.-J. Kim, Ma. Čertický and R. Kelly, “StarCraft AI Competitions, Bots and Tournament Manager Software,” IEEE Transaction on Games, 2018, 11(3), pp. 227–237, doi: 10.1109/TG.2018.2883499.
  5. O. Vinyals, I. Babuschkin et al., “Grandmaster level in StarCraft II using multi-agent reinforcement learning,” Nature, 2019, 575, pp. 350–354, http://dx.doi.org/10.1038/s41586-019-1724-z.
  6. B. G. Weber and M. Mateas, “A data mining approach to strategy prediction,” IEEE Symposium on Computational Intelligence and Games, 2009, pp. 140-147, http://dx.doi.org/10.1109/CIG.2009.5286483.
  7. H. C. Cho, K. J. Kim and S. B. Cho, “Replay-based strategy prediction and build order adaptation for StarCraft AI bots,” IEEE Conference on Computational Intelligence in Games (CIG), 2013, pp. 1-7, http://dx.doi.org/10.1109/CIG.2013.6633666.
  8. G. Synnaeve and P. Bessière, “A Dataset for StarCraft AI & an Example of Armies Clustering,” Artificial Intelligence in Adversarial Real-Time Games, 2012, https://arxiv.org/abs/1211.4552.
  9. W. Gong, X. Zhang, B. Deng and X. Xu, “Palmprint Recognition Based on Convolutional Neural Network-Alexnet,” Federated Conference on Computer Science and Information Systems, FedCSIS 2019, 18, ACSIS, pp. 313–316, http://dx.doi.org/10.15439/2019F248.