Abstract
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.
Highlights
Gomoku is a two-player board game that originated in ancient China
As convolutional neural networks (CNN)-based decision-making determines a single optimal position in the same recognized Gomoku board state, some cases arise where a stone cannot be placed in the relevant position
Cao et al presented a Gomoku artificial intelligence (AI) model using an algorithm that combined the upper confidence bounds that were applied to the trees (UCT) [12] and adaptive dynamic programming (ADP) [13,14]
Summary
Gomoku is a two-player board game that originated in ancient China. Two players alternate in placing a stone of their choice of color, and the player who first completes the five-in-a-row horizontally, vertically, or diagonally wins the game. Efficient Gomoku board recognition and decision-making was made possible while using a convolution layer of the deep-learning convolutional neural networks (CNN) algorithm [3]. As CNN-based decision-making determines a single optimal position in the same recognized Gomoku board state, some cases arise where a stone cannot be placed in the relevant position. We propose an improved reinforcement learning-based high-level decision algorithm while using CNN. We verify the performance of the proposed reinforcement learning algorithm by applying it to Gomoku. We verify the proposed method of Gomoku AI in GuPyEngine, a Python-based 3D simulation platform. This paper is expected to contribute to the field of incremental algorithms of reinforcement learning and deep learning-based 3D simulation by introducing the functions and performance of GuPyEngine.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
