SvgAI - Training Methods Analysis of Artificial Intelligent Agent to use SVG Editor

Anh H. Dang*, Wataru Kameyama

*この研究の対応する著者

研究成果: Conference contribution

抄録

Deep reinforcement learning has been successfully used to train artificial intelligent (AI) agents, which outperforms humans in many tasks. The objective of this research is to train an AI agent to draw SVG images by using scalable vector graphic (SVG) editor with deep reinforcement learning, where the AI agent is to draw SVG images that are similar as much as possible to the given target raster images. In this paper, we propose framework to train the AI agent by value-function based Q-learning and policy-gradient based learning methods. With Q-learning based method, we find that it is crucial to distinguish the action space into two sets to apply a different exploration policy on each set during the training process. Evaluations show that our proposed dual ϵ-greedy exploration policy greatly stabilizes the training process and increases the accuracy of the AI agent. On the other hand, policy-gradient based training does not depend on external reward function. However, it is hard to implement especially in the environment with a large action space. To overcome this difficulty, we propose a strategy similar to the dynamic programming method to allow the agent to generate training samples by itself. In our evaluation, the highest score is archived by the agent trained by this proposed method. SVG images produced by the proposed AI agent have also superior quality compared to popular raster-to-SVG conversion softwares.

本文言語English
ホスト出版物のタイトル21st International Conference on Advanced Communication Technology
ホスト出版物のサブタイトルICT for 4th Industrial Revolution!, ICACT 2019 - Proceeding
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1159-1166
ページ数8
ISBN(電子版)9791188428021
DOI
出版ステータスPublished - 2019 4 29
イベント21st International Conference on Advanced Communication Technology, ICACT 2019 - Pyeongchang, Korea, Republic of
継続期間: 2019 2 172019 2 20

出版物シリーズ

名前International Conference on Advanced Communication Technology, ICACT
2019-February
ISSN(印刷版)1738-9445

Conference

Conference21st International Conference on Advanced Communication Technology, ICACT 2019
国/地域Korea, Republic of
CityPyeongchang
Period19/2/1719/2/20

ASJC Scopus subject areas

  • 電子工学および電気工学

フィンガープリント

「SvgAI - Training Methods Analysis of Artificial Intelligent Agent to use SVG Editor」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル