TY - GEN
T1 - Analyses of Tabular AlphaZero on NoGo
AU - Hsueh, Chu Hsuan
AU - Ikeda, Kokolo
AU - Nam, Sang Gyu
AU - Wu, I. Chen
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - The AlphaZero algorithm has been shown to achieve superhuman levels of plays in chess, shogi, and Go. This paper presents analytic investigations of the algorithm on NoGo, a variant of Go that players cannot capture the opponents' stones. More specifically, lookup tables are employed for learning instead of deep neural networks, referred to as tabular AlphaZero. One goal of this work is to investigate how the algorithm is influenced by hyper-parameters. Another goal is to investigate whether the optimal plays and theoretical values can be learned. One of the hyper-parameters is thoroughly analyzed in the experiments. The results show that the tabular AlphaZero can learn the theoretical values and optimal plays in many settings of the hyper-parameter. Also, NoGo on different board sizes is compared, and the learning difficulty is shown to relate to the game complexity.
AB - The AlphaZero algorithm has been shown to achieve superhuman levels of plays in chess, shogi, and Go. This paper presents analytic investigations of the algorithm on NoGo, a variant of Go that players cannot capture the opponents' stones. More specifically, lookup tables are employed for learning instead of deep neural networks, referred to as tabular AlphaZero. One goal of this work is to investigate how the algorithm is influenced by hyper-parameters. Another goal is to investigate whether the optimal plays and theoretical values can be learned. One of the hyper-parameters is thoroughly analyzed in the experiments. The results show that the tabular AlphaZero can learn the theoretical values and optimal plays in many settings of the hyper-parameter. Also, NoGo on different board sizes is compared, and the learning difficulty is shown to relate to the game complexity.
KW - AlphaZero
KW - NoGo
KW - Tabular
UR - http://www.scopus.com/inward/record.url?scp=85103812158&partnerID=8YFLogxK
U2 - 10.1109/TAAI51410.2020.00054
DO - 10.1109/TAAI51410.2020.00054
M3 - Conference contribution
AN - SCOPUS:85103812158
T3 - Proceedings - 25th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2020
SP - 254
EP - 259
BT - Proceedings - 25th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2020
Y2 - 3 December 2020 through 5 December 2020
ER -