English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We formulate the problem of learning to imitate multiple, non-deterministicteachers with minimal interaction cost. Rather than learning a specific policyas in standard imitation learning, the goal in this problem is to learn adistribution over a policy space. We first present a general framework thatefficiently models and estimates such a distribution by learning continuousrepresentations of the teacher policies. Next, we develop ActivePerformance-Based Imitation Learning (APIL), an active learning algorithm forreducing the learner-teacher interaction cost in this framework. By makingquery decisions based on predictions of future progress, our algorithm avoidsthe pitfalls of traditional uncertainty-based approaches in the face of teacherbehavioral uncertainty. Results on both toy and photo-realistic navigationtasks show that APIL significantly reduces the numbers of interactions withteachers without compromising on performance. Moreover, it is robust to variousdegrees of teacher behavioral uncertainty.

Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms