Spring 2017

Interactively Learning Robot Objective Functions

Monday, Feb. 13, 2017 1:30 pm2:15 pm PST

Add to Calendar


Calvin Lab Auditorium

Inverse Reinforcement Learning enables robots to learn objective functions by observing expert behavior, but implicitly assumes that the robot is a passive observer and that the person is an uninterested expert. In this talk, I will share our recent works in making this learning process interactive, where humans teach rather than provide expert demonstrations, and robots act to actively gather information to showcase what they've learned.