Generative Adversarial Network for Imitation Learning from Single Demonstration

Tho Nguyen Duc, Chanh Minh Tran, Phan Xuan Tan, Eiji Kamioka

Research output: Contribution to journalArticlepeer-review

Abstract

Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, a Generative Adversarial Network-based model is proposed which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing considered tasks despite the limitation in the number of expert demonstrations, which clearly indicate the potential of our model.

Original languageEnglish
Pages (from-to)1350-1355
Number of pages6
JournalBaghdad Science Journal
Volume18
Issue number4
DOIs
Publication statusPublished - 2021

Keywords

  • Deep Learning
  • Few-shot Learning
  • Generative Adversarial Network
  • Imitation Learning
  • One-shot Learning

ASJC Scopus subject areas

  • Computer Science(all)
  • Chemistry(all)
  • Mathematics(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Physics and Astronomy(all)

Fingerprint

Dive into the research topics of 'Generative Adversarial Network for Imitation Learning from Single Demonstration'. Together they form a unique fingerprint.

Cite this