Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery

arXiv:2404.07185v1 Announce Type: cross
Abstract: Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting …

abstract applications arxiv cs.ai cs.lg cs.ro decision interactions low making mistakes objects observable prior processes robotic robotic surgery surgery tasks type via