Hyper-parameter Optimization for Monte Carlo Tree Search using Self-play

• 발행기관: 한국스마트미디어학회
• 저자명: 이진선(Jin-Seon Lee) 오일석(Il-Seok Oh)
• 간행물 정보: 『스마트미디어저널』Vol9, No.4, 36~43쪽, 전체 8쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2020.12.30

영문 초록

The Monte Carlo tree search (MCTS) is a popular method for implementing an intelligent game program. It has several hyper-parameters that require an optimization for showing the best performance. Due to the stochastic nature of the MCTS, the hyper-parameter optimization is difficult to solve. This paper uses the self-playing capability of the MCTS-based game program for optimizing the hyper-parameters. It seeks a winner path over the hyper-parameter space while performing the self-play. The top-q longest winners in the winner path compete for the final winner. The experiment using the 15-15-5 game (Omok in Korean name) showed a promising result.

목차

I. INTRODUCTION

II. MCTS ALGORITHM AND HYPER-PARAMETERS

III. ALGORITHM FOR HYPER-PARAMETER OPTIMIZATION OF MCTS

IV. m-n-k GAME AS A TESTBED

V. EXPERIMENTS

VI. CONCLUSIONS

REFERENCES

키워드

Machine learning Hyper-parameter optimization Monte Carlo tree search m-n-k game