Learning Robot Policies from Imperfect Teachers (Taylor Kessler Faulkner, UT Austin)

Jan 21, 2022 01:30 PM Learning Robot Policies from Imperfect Teachers Taylor Kessler Faulkner (UT Austin) Abstract: Robots learning in the wild can utilize input from human teachers to improve their learning capabilities. However, people can be imperfect teachers, which can negatively affect learning when robots expect a teacher to be a constantly present and correct oracle. Towards addressing this issue, we create algorithms for robots learning from imperfect teachers, who may be inattentive to the robot or give inaccurate information. These algorithms are based in Interactive Reinforcement Learning (interactive RL), which enables robots to take information from interactions with both their environmental reward function and additional feedback or advice from their teachers. These algorithms will allow robots to learn with or without human attention and to utilize both correct and incorrect feedback, giving more people the capability to successfully teach a robot. Biography: Taylor Kessler Fau