Umělá inteligence pro strategické počítačové hry hrané v reálném čase založená na prohledávání stavového prostoru

• Thesis title in Czech: Umělá inteligence pro strategické počítačové hry hrané v reálném čase založená na prohledávání stavového prostoru
• Thesis title in English: Search-based Artificial Players for Real-time Strategy Games
• Key words: umělá inteligence|prohledávání stavového prostoru|strategické počítačové hry|hry v reálném čase
• English key words: artificial intelligence|search-based methods|computer games|real-time strategy games
• Academic year of topic announcement: 2021/2022
• Thesis type: dissertation
• Department: Department of Software and Computer Science Education (32-KSVI)
• Supervisor: Mgr. Jakub Gemrot, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 19.09.2022
• Date of assignment: 19.09.2022
• Confirmed by Study dept. on: 29.09.2022

Guidelines

Modern games are one of the primary sources of tough problems for artificial intelligence. With the advent of computers and computer games, a genre called real-time strategy (RTS) has emerged, the games of which are particularly challenging to solve due to their large branching factor and limited amount of time to find a good move at least. The focus of this thesis is to connect on the ongoing research in this area by reviewing strength of existing algorithms for RTS and formulation, implementation and testing of new domain-specific enhancements for search-based artificial players. Results are expected to be presented in appropriate peer-reviewed conferences and journals.

References

Browne, C. B., Powley, E., Whitehouse, D., Lucas, S. M., Cowling, P. I., Rohlfshagen, P., ... & Colton, S. (2012). A survey of monte carlo tree search methods. IEEE Transactions on Computational Intelligence and AI in games, 4(1), 1-43.
Świechowski, M., Godlewski, K., Sawicki, B., & Mańdziuk, J. (2021). Monte Carlo tree search: A review of recent modifications and applications. arXiv preprint arXiv:2103.04931.
Moraes, R., Mariño, J., & Lelis, L. (2018, September). Nested-greedy search for adversarial real-time games. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 14, No. 1, pp. 67-73).
Ontanón, S., & Buro, M. (2015, June). Adversarial hierarchical-task network planning for complex real-time games. In Twenty-Fourth International Joint Conference on Artificial Intelligence.
Moraes, R. O., Marino, J. R., Lelis, L. H., & Nascimento, M. A. (2018, September). Action abstractions for combinatorial multi-armed bandit tree search. In Fourteenth Artificial Intelligence and Interactive Digital Entertainment Conference.
Ouessai, A., Salem, M., & Mora, A. M. (2020, August). Improving the performance of mcts-based µrts agents through move pruning. In 2020 IEEE Conference on Games (CoG) (pp. 708-715). IEEE.
Xu, X., Yang, M., & Li, G. (2018). Adaptive CGF commander behavior modeling through HTN guided Monte Carlo tree search. Journal of Systems Science and Systems Engineering, 27(2), 231-249.