Active Imitation Learning with Noisy Guidance

Kianté Brantley, Amr Sharaf, Hal Daumé III


Abstract
Imitation learning algorithms provide state-of-the-art results on many structured prediction tasks by learning near-optimal search policies. Such algorithms assume training-time access to an expert that can provide the optimal action at any queried state; unfortunately, the number of such queries is often prohibitive, frequently rendering these approaches impractical. To combat this query complexity, we consider an active learning setting in which the learning algorithm has additional access to a much cheaper noisy heuristic that provides noisy guidance. Our algorithm, LEAQI, learns a difference classifier that predicts when the expert is likely to disagree with the heuristic, and queries the expert only when necessary. We apply LEAQI to three sequence labelling tasks, demonstrating significantly fewer queries to the expert and comparable (or better) accuracies over a passive approach.
Anthology ID:
2020.acl-main.189
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2093–2105
Language:
URL:
https://aclanthology.org/2020.acl-main.189
DOI:
10.18653/v1/2020.acl-main.189
Bibkey:
Cite (ACL):
Kianté Brantley, Amr Sharaf, and Hal Daumé III. 2020. Active Imitation Learning with Noisy Guidance. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2093–2105, Online. Association for Computational Linguistics.
Cite (Informal):
Active Imitation Learning with Noisy Guidance (Brantley et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.189.pdf
Software:
 2020.acl-main.189.Software.tgz
Video:
 http://slideslive.com/38929087
Code
 xkianteb/leaqi
Data
CoNLL 2003SemEval-2017 Task-10