Abstract
Research on artificial intelligence (AI) has experienced a substantial stride since the advent of the AlphaGo, progressing the application of deep learning techniques for the game application. However, significant research is still unpublished in the field of turn-based strategy games, owing to the complexity of the game structure and its computational problem. To apply deep learning to turn-based strategy games, a policy network created from match data was developed from learning game records. The neural network design used as a policy network is integrated into the turn-based strategy games, using a recurrent neural network to reduce the number of output neurons and to divide the output structure into original positions, destinations, and attack positions. Using the state and action data as a database, the game data are generated from the learning map based on the competition with the Monte Carlo Tree Search (MCTS) algorithm. However, the produced policy network demonstrates a superior performance against the MCTS algorithm with a winning rate of over \(50\%\) on the learning maps, and over \(40\%\) on the validation maps. In the game, the thinking time for the deep learning is extremely short since this it is performed by inference only, whereas MCTS thinking the time is approximately 5 to 10 s per move.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7674), 354–359 (2017)
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140–1144 (2018)
Fujiki, T., Ikeda, K., Viennot, S.: A platform for turn-based strategy games, with a comparison of Monte-Carlo algorithms. In: IEEE Conference on Computational Intelligence and Games, CIG2015, pp. 407–414 (2015)
TUBSTAP Homepage. http://www.jaist.ac.jp/is/labs/ikeda-lab/tbs_eng/index.htm. Accessed 10 Apr 2019
Stanescu, M., Barriga, N.A., Hess, A., et al.: Evaluating real-time strategy game states using convolutional neural networks. In: IEEE Computational Intelligence and Games (CIG) (2016)
Kato, C., Miwa, M., Tsuruoka, Y., Chikayama, T.: UCT and its enhancement for tactical decisions in turn-based strategy games. In: Game Programming Workshop 2013, pp. 138–145 (2013). (in Japanese)
Sato, N., Ikeda, K.: Three types of forward pruning techniques to apply alpha beta algorithm to turn-based strategy game. In: IEEE Conference on Computational Intelligence and Games, CIG2016, pp. 294–301 (2016)
Sato, N., Fujiki, T., Ikeda, K.: An approach to evaluate turn-based strategy game positions with offline tree searches in simplified games. In: Game Programming Workshop 2015, pp. 61–68 (2015). (in Japanese)
Kimura, T.: Simple data representation method with deep learning for turn-based strategy game. IPSJ SIG technical reports, 2019-GI-41, vol. 5, pp. 1–8 (2019). (in Japanese)
Kimura, T., Ikeda, K.: Offering new benchmark maps for turn based strategy game. In: Game Programming Workshop 2016, pp. 36–43 (2016). (in Japanese)
Game AI Tournaments Homepage (GAT). http://minerva.cs.uec.ac.jp/gat_uec/wiki.cgi?page=FrontPage. Accessed 10 Apr 2019. (in Japanese)
Game Programming Workshop Homepage (GPW). http://www.ipsj.or.jp/sig/gi/gpw/index-e.html. Accessed 10 Apr 2019
Tesauro, G.: Neurogammon wins computer Olympiad. Neural Comput. 1(3), 321–323 (1989)
Clark, C., Storkey, A.: Training deep convolutional neural networks to play Go. In: ICML 2015 Proceedings of the 32nd International Conference on International Conference on Machine Learning, vol. 37, pp. 1766–1774. JMLR (2015)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 1724–1734 (2014)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kimura, T., Ikeda, K. (2020). Designing Policy Network with Deep Learning in Turn-Based Strategy Games. In: Cazenave, T., van den Herik, J., Saffidine, A., Wu, IC. (eds) Advances in Computer Games. ACG 2019. Lecture Notes in Computer Science(), vol 12516. Springer, Cham. https://doi.org/10.1007/978-3-030-65883-0_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-65883-0_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65882-3
Online ISBN: 978-3-030-65883-0
eBook Packages: Computer ScienceComputer Science (R0)