Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Karol Arndt, Oliver Struckmeier, Ville Kyrki

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)
89 Downloads (Pure)

Abstract

Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to be available during the adaptation. In this paper, we present domain curiosity—a method of training exploratory policies that are explicitly optimized to provide data that allows a model to learn about the unknown aspects of the environment. In contrast to most curiosity methods, our approach explicitly rewards learning, which makes it robust to environment noise without sacrificing its ability to learn. We evaluate the proposed method by comparing how much a model can learn about environment dynamics given data collected by the proposed approach, compared to standard curious and random policies. The evaluation is performed using a toy environment, two simulated robot setups, and on a real-world haptic exploration task. The results show that the proposed method allows data-efficient and accurate estimation of dynamics.
Original languageEnglish
Title of host publicationProceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PublisherIEEE
Pages1259-1266
Number of pages8
ISBN (Electronic)978-1-6654-1714-3
DOIs
Publication statusPublished - 16 Dec 2021
MoE publication typeA4 Conference publication
EventIEEE/RSJ International Conference on Intelligent Robots and Systems - Prague, Czech Republic
Duration: 27 Sept 20211 Oct 2021

Publication series

NameProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0858

Conference

ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS
Country/TerritoryCzech Republic
CityPrague
Period27/09/202101/10/2021

Keywords

  • Training
  • Adaptation models
  • Predictive models
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation'. Together they form a unique fingerprint.

Cite this