Active Imitation Learning with Noisy Guidance
This work addresses the query efficiency problem for practitioners using imitation learning in structured prediction, though it is incremental as it builds on existing active learning methods.
The paper tackles the high query cost in imitation learning by introducing an active learning approach that uses a noisy heuristic to reduce expert queries, achieving comparable or better accuracy with significantly fewer queries on sequence labeling tasks.
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.