Audrey Huang, MS Student
My current research with ACMI Lab lies on the theoretical side of risk-sensitive reinforcement learning, and I have broad interests in safe and human-aligned RL. I recently obtained my master’s from MLD and before that was an undergrad at Caltech. I enjoy sport climbing in my spare time and managed to learn a bad ollie over the course of quarantine.
Research Interests: RL, Imitation Learning, Risk-Aversion, Safety
Publications
Off-Policy Risk Assessment for Markov Decision Processes
Audrey Huang, Liu Leqi, Kamyar Azizzadenesheli, Zachary Lipton
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022Off-Policy Risk Assessment in Contextual Bandits
Audrey Huang, Liu Leqi, Zachary Lipton, Kamyar Azizzadenesheli
Advances in Neural Information Processing Systems (NeurIPS), 2021