TY - JOUR
T1 - Enhanced reinforcement learning method combining one-hot encoding-based vectors for cnn-based alternative high-level decisions
AU - Gu, Bonwoo
AU - Sung, Yunsick
N1 - Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2021/2/1
Y1 - 2021/2/1
N2 - Gomoku is a two-player board game that originated in ancient China. There are various cases of developing Gomoku using artificial intelligence, such as a genetic algorithm and a tree search algorithm. Alpha-Gomoku, Gomoku AI built with Alpha-Go’s algorithm, defines all possible situations in the Gomoku board using Monte-Carlo tree search (MCTS), and minimizes the probability of learning other correct answers in the duplicated Gomoku board situation. However, in the tree search algorithm, the accuracy drops, because the classification criteria are manually set. In this paper, we propose an improved reinforcement learning-based high-level decision approach using convolutional neural networks (CNN). The proposed algorithm expresses each state as One-Hot Encoding based vectors and determines the state of the Gomoku board by combining the similar state of One-Hot Encoding based vectors. Thus, in a case where a stone that is determined by CNN has already been placed or cannot be placed, we suggest a method for selecting an alternative. We verify the proposed method of Gomoku AI in GuPyEngine, a Python-based 3D simulation platform.
AB - Gomoku is a two-player board game that originated in ancient China. There are various cases of developing Gomoku using artificial intelligence, such as a genetic algorithm and a tree search algorithm. Alpha-Gomoku, Gomoku AI built with Alpha-Go’s algorithm, defines all possible situations in the Gomoku board using Monte-Carlo tree search (MCTS), and minimizes the probability of learning other correct answers in the duplicated Gomoku board situation. However, in the tree search algorithm, the accuracy drops, because the classification criteria are manually set. In this paper, we propose an improved reinforcement learning-based high-level decision approach using convolutional neural networks (CNN). The proposed algorithm expresses each state as One-Hot Encoding based vectors and determines the state of the Gomoku board by combining the similar state of One-Hot Encoding based vectors. Thus, in a case where a stone that is determined by CNN has already been placed or cannot be placed, we suggest a method for selecting an alternative. We verify the proposed method of Gomoku AI in GuPyEngine, a Python-based 3D simulation platform.
KW - Convolutional neural-networks
KW - Game artificial intelligence
KW - Gomoku
KW - One-hot encoding
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85100559302&partnerID=8YFLogxK
U2 - 10.3390/app11031291
DO - 10.3390/app11031291
M3 - Article
AN - SCOPUS:85100559302
SN - 2076-3417
VL - 11
SP - 1
EP - 15
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 3
M1 - 1291
ER -