Enhanced reinforcement learning method combining one-hot encoding-based vectors for cnn-based alternative high-level decisions

Bonwoo Gu, Yunsick Sung

Research output: Contribution to journalArticlepeer-review

28 Scopus citations

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.

Original languageEnglish
Article number1291
Pages (from-to)1-15
Number of pages15
JournalApplied Sciences (Switzerland)
Volume11
Issue number3
DOIs
StatePublished - 1 Feb 2021

Keywords

  • Convolutional neural-networks
  • Game artificial intelligence
  • Gomoku
  • One-hot encoding
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Enhanced reinforcement learning method combining one-hot encoding-based vectors for cnn-based alternative high-level decisions'. Together they form a unique fingerprint.

Cite this