@article {IOPORT.05580265,
    author       = {Thomaz, Andrea L. and Breazeal, Cynthia},
    title        = {Teachable robots: understanding human teaching behavior to build more effective robot learners.},
    year         = {2008},
    journal      = {Artificial Intelligence},
    volume       = {172},
    number       = {6-7},
    issn         = {0004-3702},
    pages        = {716-737},
    publisher    = {Elsevier Science Publishers, Amsterdam},
    doi          = {10.1016/j.artint.2007.09.009},
    abstract     = {Summary: While Reinforcement Learning (RL) is not traditionally designed for interactive supervisory input from a human teacher, several works in both robot and software agents have adapted it for human input by letting a human trainer control the reward signal. In this work, we experimentally examine the assumption underlying these works, namely that the human-given reward is compatible with the traditional RL reward signal. We describe an experimental platform with a simulated RL robot and present an analysis of real-time human teaching behavior found in a study in which untrained subjects taught the robot to perform a new task. We report three main observations on how people administer feedback when teaching a Reinforcement Learning agent: (a) they use the reward channel not only for feedback, but also for future-directed guidance; (b) they have a positive bias to their feedback, possibly using the signal as a motivational channel; and (c) they change their behavior as they develop a mental model of the robotic learner. Given this, we made specific modifications to the simulated RL robot, and analyzed and evaluated its learning behavior in four follow-up experiments with human trainers. We report significant improvements on several learning measures. This work demonstrates the importance of understanding the human-teacher/robot-learner partnership in order to design algorithms that support how people want to teach and simultaneously improve the robot's learning behavior.},
    identifier   = {05580265},
}