Part of the book series:Lecture Notes in Computer Science ((LNCS,volume 14358))
Included in the following conference series:
585Accesses
Abstract
A Tripeaks variant game, derived from the classic card game Tripeaks, is gaining popularity among players. In order to evaluate the difficulty of Tripeaks variant games and assist in level design, this paper investigates the playing strategies for Tripeaks variant games. Firstly, three heuristic strategies based on player experience are proposed. Then, reinforcement learning agents are trained and tested on different datasets to evaluate their generalization performance. The experiments demonstrate that Tripeaks variant games have a high degree of randomness and also possess certain strategies. The reinforcement learning agents have some generalization ability, but cannot handle the rich layouts of Tripeaks variant games. Heuristic strategies have stable and efficient performance, and are more suitable for difficulty detection and level design assistance in Tripeaks variant games.
This work was supported in part by the Hangzhou Normal University under Grant 1115B20500409.
This is a preview of subscription content,log in via an institution to check access.
Access this chapter
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
- Chapter
- JPY 3498
- Price includes VAT (Japan)
- eBook
- JPY 9151
- Price includes VAT (Japan)
- Softcover Book
- JPY 11439
- Price includes VAT (Japan)
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature518(7540), 529–533 (2015)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature529(7587), 484–489 (2016)
Brown, N., Sandholm, T.: Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. Science359(6374), 418–424 (2018)
Berner, C.,et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprintarXiv:1912.06680 (2019)
Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature575(7782), 350–354 (2019)
Justesen, N., Torrado, R.R., Bontrager, P., Khalifa, A., Togelius, J., Risi, S.: Illuminating generalization in deep reinforcement learning through procedural level generation. arXiv preprintarXiv:1806.10729 (2018)
Zha, D., Lai, K.H., Cao, Y., Huang, S., Wei, R., Guo, J., Hu, X.: Rlcard: A toolkit for reinforcement learning in card games. arXiv preprintarXiv:1910.04376 (2019)
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science362(6419), 1140–1144 (2018)
Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature588(7839), 604–609 (2020)
Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: First return, then explore. Nature590(7847), 580–586 (2021)
Moravčík, M., et al.: Deepstack: Expert-level artificial intelligence in heads-up no-limit poker. Science356(6337), 508–513 (2017)
Yin, Q., Yang, J., Ni, W., Liang, B., Huang, K.: Ai in games: techniques, challenges and opportunities. arXiv preprintarXiv:2111.07631 (2021)
Jiang, Q., Li, K., Du, B., Chen, H., Fang, H.: Deltadou: Expert-level Doudizhu AI through self-play. In: IJCAI, pp. 1265–1271 (2019)
Zha, D., et al.: Douzero: Mastering doudizhu with self-play deep reinforcement learning. In: International Conference on Machine Learning, pp. 12333–12344. PMLR (2021)
Oeschger, P.: Applying deep reinforcement learning to the card game cego. informatik J.13, 91–99 (2022)
Yi, H.: Some case studies on the efficiency of reinforcement learning in card game solitaire with uncertainty (2021)
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv preprintarXiv:1312.5602 (2013)
Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)
Lin, L.J.: Reinforcement learning for robots using neural networks. Carnegie Mellon University (1992)
Author information
Authors and Affiliations
Hangzhou Normal University, Hangzhou, Zhejiang, 311121, China
Yijie Gao & Shuchang Xu
Beijing DAILYBREAD CO., LTD, Beijing, 100192, China
Shunpeng Du
- Yijie Gao
You can also search for this author inPubMed Google Scholar
- Shuchang Xu
You can also search for this author inPubMed Google Scholar
- Shunpeng Du
You can also search for this author inPubMed Google Scholar
Corresponding author
Correspondence toShuchang Xu.
Editor information
Editors and Affiliations
Dalian University of Technology, Dalian, China
Huchuan Lu
University of Sydney, Sydney, NSW, Australia
Wanli Ouyang
Shenzhen University, Shenzhen, China
Hui Huang
Tsinghua University, Beijing, China
Jiwen Lu
Dalian University of Technology, Dalian, China
Risheng Liu
Institute of Automation, CAS, Beijing, China
Jing Dong
University of Technology Sydney, Sydney, NSW, Australia
Min Xu
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, Y., Xu, S., Du, S. (2023). Research on Strategies for Tripeaks Variant with Various Layouts. In: Lu, H.,et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14358. Springer, Cham. https://doi.org/10.1007/978-3-031-46314-3_7
Download citation
Published:
Publisher Name:Springer, Cham
Print ISBN:978-3-031-46313-6
Online ISBN:978-3-031-46314-3
eBook Packages:Computer ScienceComputer Science (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative