Interactive Reinforcement Learning from Imperfect Teachers

摘要

Robots can use information from people to improve learning speed or quality. However, people can have short attention spans and misunderstand tasks. Our work addresses these issues with algorithms for learning from inattentive teachers that take advantage of feedback when people are present, and an algorithm for learning from inaccurate teachers that estimates which state-action pairs receive incorrect feedback. These advances will enhance robots' ability to take advantage of imperfect feedback from human teachers.