Open bahriddin opened 6 years ago
Also, I suggest we should test the algorithm performance with some public Gomoku/Abalone engines. I list some below after researching.
Gomoku
Yixin, developed by Kai Sun, is the winner of the 13th, 14th, 15th, 16th, 17th and 18th Gomocup. It is widely known as the best Gomoku AI in the world. http://www.aiexp.info/pages/yixin.html
Gomocup – The Gomoku AI Tournament Gomocup released different versions of the top 39 AI in 2017 tournament, including Yixin listed above. http://gomocup.org/download-gomoku-ai/
Abalone
Hypothesis
Authors of recently published research Alpha Zero stated that this technique could be easily generalised to other problems without significant human effort and it approached better than other state-of-the-art alternatives [1]. They tested the system in 3 board games, specifically, Go, Chess and Shogi. We would like to check it in the different game(s) with closer game-space and game-tree complexities.
Questions
Methods
This list can be modified in the later stages of the research.
Candidate Games
We would like to find an answer to our research questions using at least one of this board games:
Gomoku
-- Wikipedia
It's space complexity in 15x15 board is about 3225 while game tree complexity 1070 [3].
Abalone
-- Wikipedia
It's space complexity is about 6.5 1023 while average branching factor 60 and game tree complexity 5 10154 [4].
Related Work: