Domain adaptation for imitation learning using generative adversarial network

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

Research output: Contribution to journalArticlepeer-review

Abstract

Imitation learning is an effective approach for an autonomous agent to learn control policies when an explicit reward function is unavailable, using demonstrations provided from an expert. However, standard imitation learning methods assume that the agents and the demonstrations provided by the expert are in the same domain configuration. Such an assumption has made the learned policies difficult to apply in another distinct domain. The problem is formalized as domain adaptive imitation learning, which is the process of learning how to perform a task optimally in a learner domain, given demonstrations of the task in a distinct expert domain. We address the problem by proposing a model based on Generative Adversarial Network. The model aims to learn both domain-shared and domain-specific features and utilizes it to find an optimal policy across domains. The experimental results show the effectiveness of our model in a number of tasks ranging from low to complex high-dimensional.

Original languageEnglish
Article number4718
JournalSensors
Volume21
Issue number14
DOIs
Publication statusPublished - 2021 Jul 2

Keywords

  • Domain adaptive imitation learning
  • Generative adversarial network
  • Imitation learning

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Domain adaptation for imitation learning using generative adversarial network'. Together they form a unique fingerprint.

Cite this