Symbol Grounding and Task Learning from Imperfect Corrections

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

Abstract

This paper describes a method for learning from a teacher’s potentially unreliable corrective feedback in an interactive task learning setting. The graphical model uses discourse coherence to jointly learn symbol grounding, domain concepts and valid plans. Our experiments show that the agent learns its domain-level task in spite of the teacher’s mistakes.
Original languageEnglish
Title of host publicationSecond International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
Place of PublicationACL-IJNLP, 2021
PublisherAssociation for Computational Linguistics (ACL)
Pages1-10
Number of pages10
ISBN (Electronic)978-1-954085-78-7
DOIs
Publication statusPublished - 1 Aug 2021
EventSecond International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics - Online @ ACL-IJCNLP 2021
Duration: 5 Aug 20216 Aug 2021
https://splu-robonlp2021.github.io/

Workshop

WorkshopSecond International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
Abbreviated titleSpLU-RoboNLP 2021
Period5/08/216/08/21
Internet address

Fingerprint

Dive into the research topics of 'Symbol Grounding and Task Learning from Imperfect Corrections'. Together they form a unique fingerprint.

Cite this