Pre-VIVA talk: Exploiting Generics During Interactive Task Learning
Date:
Thu, 02/10/2025 - 13:00
Location:
Informatics Forum. G.03
Speaker:
Jay Park
University of Edinburgh
Abstract: Recent machine learning (ML) research has chiefly focused on
optimising performance on tasks whose structure is fully specified in
advance. For instance, with assembly tasks, the agent has complete
knowledge prior to deployment about which component parts form valid
structures; e.g., that fire trucks must have ladders. The agent may
not know, and will have to learn, what fire trucks or what ladders
look like, but they have a complete and accurate hypothesis space of