no code implementations • 13 Jul 2023 • Qiuyi, Zhang, Michael S. Lee, Sherol Chen
Beliefs and values are increasingly being incorporated into our AI systems through alignment processes, such as carefully curating data collection principles or regularizing the loss function used for training.
no code implementations • 3 Mar 2022 • Michael S. Lee, Henny Admoni, Reid Simmons
We propose to incorporate the learner's current understanding of the robot's decision making into our model of human IRL, so that a robot can select demonstrations that maximize the human's understanding.
no code implementations • 4 Oct 2019 • John S. Hyatt, Michael S. Lee
Validation accuracy is a necessary, but not sufficient, measure of a neural network classifier's quality.