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

This paper addresses the problem of learning a task from demonstration. Weadopt the framework of inverse reinforcement learning, where tasks arerepresented in the form of a reward function. Our contribution is a novelactive learning algorithm that enables the learning agent to query the expertfor more informative demonstrations, thus leading to more sample-efficientlearning. For this novel algorithm (Generalized Binary Search for InverseReinforcement Learning, or GBS-IRL), we provide a theoretical bound on samplecomplexity and illustrate its applicability on several different tasks. To ourknowledge, GBS-IRL is the first active IRL algorithm with provable samplecomplexity bounds. We also discuss our method in light of other existingmethods in the literature and its general applicability in multi-classclassification problems. Finally, motivated by recent work on learning fromdemonstration in robots, we also discuss how different forms of human feedbackcan be integrated in a transparent manner in our learning framework.

Multi-class Generalized Binary Search for Active Inverse Reinforcement Learning