Abstract
Real-Time Strategy (RTS) games are one of the most complex and challenging areas from the perspective of artificial intelligence. Besides, some real-time wargaming platforms not only have the characteristics of large state-action space, incomplete information, and instantaneity but also have not many decision-making in the whole game. In this paper, we propose a data augmentation method and a hybrid neural network model combining Gated Recurrent Unit(GRU) network and Pointer network, which can select an action unit to execute the decision and a target unit to be attacked at a few time points in the game. The hybrid neural network model and data augmentation method are evaluated in a war simulation platform. Experimental results show that in the unit selection of real-time strategy games, the hybrid network model and data augmentation method outperform the hybrid neural network without data augmentation or simply using pointer network model.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Barriga, N., Stanescu, M., Buro, M.: Puppet search: enhancing scripted behavior by look-ahead search with applications to real-time strategy games. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 11, pp. 9–15 (2015)
Barriga, N., Stanescu, M., Buro, M.: Combining strategic learning with tactical search in real-time strategy games. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 13, pp. 9–15 (2017)
Che, Z., Purushotham, S., Cho, K., Sontag, D., Liu, Y.: Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8(1), 1–12 (2018)
Churchill, D., Buro, M.: Portfolio greedy search and simulation for large-scale combat in StarCraft. In: 2013 IEEE Conference on Computational Intelligence in Games (CIG), pp. 1–8. IEEE (2013)
Churchill, D., Saffidine, A., Buro, M.: Fast heuristic search for RTS game combat scenarios. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 8 (2012)
DataCastle: Intelligent game confrontation competition of joint operation (2020). https://encourage.dcjingsai.com/WarGame.html
Foerster, J., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 1146–1155. PMLR (2017)
Guo, B., Zhang, C., Liu, J., Ma, X.: Improving text classification with weighted word embeddings via a multi-channel TextCNN model. Neurocomputing 363, 366–374 (2019)
Han, X., Yan, H., Zhang, J., Wang, L.: Cluster-based alpha-beta search for real-time strategy games. In: IOP Conference Series: Materials Science and Engineering, vol. 435, pp. 1–10 (2018)
OpenAI.: Openai blog: Dota 2, 17 April 2018. https://blog.openai.com/dota-2/
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Shafi, K., Abbass, H.A.: A survey of learning classifier systems in games. IEEE Comput. Intell. Mag. 12(1), 42–55 (2017)
Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Vinyals, O., et al.: Grandmaster level in StarCraft ii using multi-agent reinforcement learning. Nature 575(7782), 350–354 (2019)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: International Conference on Neural Information Processing Systems, pp. 2692–2700 (2015)
Wu, B.: Hierarchical macro strategy model for MOBA game AI. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 1206–1213 (2019)
Acknowledgement
This work was supported by National Natural Science Foundation of China (Grant No. 61502274), Natural Science Foundation of Hubei (Grant No. 2015CFB336), and Open Fund of Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering (CTGU)(Grant No. 2015KLA08)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Guo, H., Zang, Z., Zhang, Z., Tian, P. (2021). Combat Unit Selection Based on Hybrid Neural Network in Real-Time Strategy Games. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1517. Springer, Cham. https://doi.org/10.1007/978-3-030-92310-5_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-92310-5_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92309-9
Online ISBN: 978-3-030-92310-5
eBook Packages: Computer ScienceComputer Science (R0)