SvgAI - Training artificial intelligent agent to use SVG editor

Anh H. Dang, Wataru Kameyama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep reinforcement learning has been successfully used to train artificial intelligent (AI) agents to outperform humans in many tasks as well as to enhance the capability in robotic automation. In this paper, we propose a framework to train an AI agent to use scalable vector graphic (SVG) editor to draw SVG images. Hence, the objective of this AI agent is to draw SVG images that are similar as much as possible to their target raster images. We find that it is crucial to distinguish the action space into two sets and apply a different exploration policy on each set during the training process. Evaluations show that our proposed dual-exploration policy greatly stabilizes the training process and increases the accuracy of the AI agent. SVG images produced by the proposed AI agent also have superior quality compared to popular raster-to-SVG conversion software.

Original languageEnglish
Title of host publicationIEEE 20th International Conference on Advanced Communication Technology
Subtitle of host publicationOpening New Era of Intelligent Things, ICACT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages132-138
Number of pages7
Volume2018-February
ISBN (Electronic)9791188428007
DOIs
Publication statusPublished - 2018 Mar 23
Event20th IEEE International Conference on Advanced Communication Technology, ICACT 2018 - Chuncheon, Korea, Republic of
Duration: 2018 Feb 112018 Feb 14

Other

Other20th IEEE International Conference on Advanced Communication Technology, ICACT 2018
CountryKorea, Republic of
CityChuncheon
Period18/2/1118/2/14

Keywords

  • Exploration Policy
  • Q-Learning
  • Reinforcement Learning
  • SVG
  • SvgAI

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'SvgAI - Training artificial intelligent agent to use SVG editor'. Together they form a unique fingerprint.

Cite this