State-Only Imitation Learning for Dexterous Manipulation

Ilija Radosavovic, Xiaolong Wang, Lerrel Pinto, Jitendra Malik

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

Abstract

Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address this, current approaches employ expert demonstrations in the form of state-action pairs, which are difficult to obtain for real-world settings such as learning from videos. In this paper, we move toward a more realistic setting and explore state-only imitation learning. To tackle this setting, we train an inverse dynamics model and use it to predict actions for state-only demonstrations. The inverse dynamics model and the policy are trained jointly. Our method performs on par with state-action approaches and considerably outperforms RL alone. By not relying on expert actions, we are able to learn from demonstrations with different dynamics, morphologies, and objects. Videos available on the { text{project page}}.

Original languageEnglish (US)
Title of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7865-7871
Number of pages7
ISBN (Electronic)9781665417143
DOIs
StatePublished - 2021
Event2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021 - Prague, Czech Republic
Duration: Sep 27 2021Oct 1 2021

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
Country/TerritoryCzech Republic
CityPrague
Period9/27/2110/1/21

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'State-Only Imitation Learning for Dexterous Manipulation'. Together they form a unique fingerprint.

Cite this