Artificial Intelligence for the strategy game Score Four
Thesis title in Czech: | Umělá inteligence pro strategickou hru Score Four |
---|---|
Thesis title in English: | Artificial Intelligence for the strategy game Score Four |
Academic year of topic announcement: | 2022/2023 |
Type of assignment: | Bachelor's thesis |
Thesis language: | angličtina |
Department: | Department of Software and Computer Science Education (32-KSVI) |
Supervisor: | Adam Dingle, M.Sc. |
Author: | hidden![]() |
Date of registration: | 27.09.2022 |
Date of assignment: | 27.09.2022 |
Confirmed by Study dept. on: | 07.10.2022 |
Guidelines |
Score Four is a three-dimensional abstract strategy game that is similar to the popular game Connect Four. Although Score Four has existed for decades, there is apparently no published literature about the game, and few computer implementations are available. In this thesis work, the student will implement Score Four and will write several artificial agents that can play the game using a variety of methods, possibly including rules-based heuristics, minimax, Monte Carlo tree search and/or reinforcement learning. The student will compare and analyze the performance of these agents, and may also consider whether it is feasible to solve the game completely (as has been done for Connect Four). |
References |
Allis, Louis Victor. "A Knowledge-Based Approach of Connect-Four." J. Int. Comput. Games Assoc. 11.4 (1988): 165.
Browne, Cameron B., et al. "A survey of Monte Carlo tree search methods." IEEE Transactions on Computational Intelligence and AI in games 4.1 (2012): 1-43. Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 2018. Yannakakis, Georgios N., and Julian Togelius. Artificial intelligence and games. New York: Springer, 2018. |