SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning

Bian Xihan, Oscar Mendez, Simon Hadfield

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

3 Citations (Scopus)

Abstract

In this work, we introduce a new perspective for learning transferable content in multi-task imitation learning. Humans are capable of transferring skills and knowledge. If we can cycle to work and drive to the store, we can also cycle to the store and drive to work. We take inspiration from this and hypothesize the latent memory of a policy network can be disentangled into two partitions. These contain either the knowledge of the environmental context for the task or the generalisable skill needed to solve the task. This allows an improved training efficiency and better generalization over previously unseen combinations of skills in the same environment, and the same task in unseen environments. We used the proposed approach to train a disentangled agent for two different multi-task IL environments. In both cases, we out-performed the SOTA by 30% in task success rate. We also demonstrated this for navigation on a real robot.

Original languageEnglish
Title of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7060-7065
Number of pages6
ISBN (Electronic)9781665479271
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022 - Kyoto, Japan
Duration: 23 Oct 202227 Oct 2022

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2022-October
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
Country/TerritoryJapan
CityKyoto
Period23/10/2227/10/22

Fingerprint

Dive into the research topics of 'SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning'. Together they form a unique fingerprint.

Cite this