Abstract
Catan is a strategic board game with many interesting properties, including multi-player, imperfect information, stochasticity, a complex state space structure (hexagonal board where each vertex, edge and face has its own features, cards for each player, etc.), and a large action space (including trading). Therefore, it is challenging to build AI agents by Reinforcement Learning (RL), without domain knowledge nor heuristics. In this paper, we introduce cross-dimensional neural networks to handle a mixture of information sources and a wide variety of outputs, and empirically demonstrate that the network dramatically improves RL in Catan. We also show that, for the first time, a RL agent can outperform jsettler, the best heuristic agent available.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Previously named The Settlers of Catan, renamed for the 5th Edition (2015).
- 2.
AMD Ryzen Threadripper 2990WX.
References
Bowling, M., Burch, N., Johanson, M., Tammelin, O.: Heads-up limit hold’em poker is solved. Science 347(6218), 145–149 (2015). https://doi.org/10.1126/science.1259433
Catan Studio and Catan GmbH: Catan base game rules & almanac 3/4 players (5th edition). https://www.catan.com/service/game-rules (2020)
Cuayáhuitl, H., Keizer, S., Lemon, O.: Strategic dialogue management via deep reinforcement learning. CoRR (2015). http://arxiv.org/abs/1511.08099
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778, June 2016. https://doi.org/10.1109/CVPR.2016.90
Li, J., et al.: Suphx: mastering mahjong with deep reinforcement learning. CoRR (2020). http://arxiv.org/abs/2003.13590
Mnih, V., et al.: Playing atari with deep reinforcement learning. NIPS Deep Learning Workshop (2013)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: The 33rd International Conference on Machine Learning, pp. 1928–1937 (2016)
Monin, J., contributors: Jsettlers2 release-2.2.00. https://github.com/jdmonin/JSettlers2/releases/tag/release-2.2.00 (2020)
Pfeiffer, M.: Reinforcement learning of strategies for settlers of catan. In: Proceedings of the International Conference on Computer Games: Artificial Intelligence, Design and Education (2004)
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140–1144 (2018). https://doi.org/10.1126/science.aar6404
Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 2nd edn. MIT Press, Cambridge, MA, USA (2018)
Szita, I., Chaslot, G., Spronck, P.: Monte-carlo tree search in settlers of catan. In: van den Herik, H.J., Spronck, P. (eds.) Advances in Computer Games, pp. 21–32. Springer, Berlin, Heidelberg (2010)
Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575, 350–354 (2019)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Xenou, K., Chalkiadakis, G., Afantenos, S.: Deep reinforcement learning in strategic board game environments. In: Slavkovik, M. (ed.) Multi-Agent Systems, pp. 233–248. Springer International Publishing, Cham (2019)
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
Gendre, Q., Kaneko, T. (2020). Playing Catan with Cross-Dimensional Neural Network. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science(), vol 12533. Springer, Cham. https://doi.org/10.1007/978-3-030-63833-7_49
Download citation
DOI: https://doi.org/10.1007/978-3-030-63833-7_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63832-0
Online ISBN: 978-3-030-63833-7
eBook Packages: Computer ScienceComputer Science (R0)