메뉴 건너뛰기
Library Notice
Institutional Access
If you certify, you can access the articles for free.
Check out your institutions.
ex)Hankuk University, Nuri Motors
Log in Register Help KOR
Subject

Comparison of Reinforcement Learning Algorithms for a 2D Racing Game Learning Agent
Recommendations
Search

2D 레이싱 게임 학습 에이전트를 위한 강화 학습 알고리즘 비교 분석

논문 기본 정보

Type
Academic journal
Author
Lee, Dongcheul (한남대학교 멀티미디어공학과)
Journal
The Institute of Internet, Broading and Communication 한국인터넷방송통신학회 논문지 한국인터넷방송통신학회 논문지 제20권 제1호 KCI Accredited Journals
Published
2020.1
Pages
171 - 176 (6page)

Usage

cover
Comparison of Reinforcement Learning Algorithms for a 2D Racing Game Learning Agent
Ask AI
Recommendations
Search

Abstract· Keywords

Report Errors
Reinforcement learning is a well-known method for training an artificial software agent for a video game. Even though many reinforcement learning algorithms have been proposed, their performance was varies depending on an application area. This paper compares the performance of the algorithms when we train our reinforcement learning agent for a 2D racing game. We defined performance metrics to analyze the results and plotted them into various graphs. As a result, we found ACER (Actor Critic with Experience Replay) achieved the best rewards than other algorithms. There was 157% gap between ACER and the worst algorithm.

Contents

No content found

References (8)

Add References

Recommendations

It is an article recommended by DBpia according to the article similarity. Check out the related articles!

Related Authors

Recently viewed articles

Comments(0)

0

Write first comments.