Active Imitation Learning with Noisy Guidance

TL;DR

This paper introduces LEAQI, an active imitation learning algorithm that reduces expert queries by leveraging a noisy heuristic, achieving comparable accuracy with fewer expert interactions.

Contribution

The paper proposes LEAQI, a novel active learning method that uses a difference classifier to selectively query an expert, improving efficiency in imitation learning with noisy guidance.

Findings

LEAQI significantly reduces expert queries.

LEAQI achieves comparable or better accuracy than passive methods.

Effective in three sequence labeling tasks.

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 labeling tasks, demonstrating significantly fewer queries to the expert and comparable (or better) accuracies over a passive approach.