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 consider the problem of learning the behavioral preferences of an expertengaged in a task from noisy and partially-observable demonstrations. This ismotivated by real-world applications such as a line robot learning fromobserving a human worker, where some observations are occluded by environmentalobjects that cannot be removed. Furthermore, robotic perception tends to beimperfect and noisy. Previous techniques for inverse reinforcement learning(IRL) take the approach of either omitting the missing portions or inferring itas part of expectation-maximization, which tends to be slow and prone to localoptima. We present a new method that generalizes the well-known Bayesianmaximum-a-posteriori (MAP) IRL method by marginalizing the occluded portions ofthe trajectory. This is additionally extended with an observation model toaccount for perception noise. We show that the marginal MAP (MMAP) approachsignificantly improves on the previous IRL technique under occlusion in bothformative evaluations on a toy problem and in a summative evaluation on anonion sorting line task by a robot.

Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise