Kevin Huang

About

Hi! I am a final year undergraduate student at Caltech, studying computer science and machine learning. My research interests include reinforcement learning, planning, and optimization. Broadly, I am interested in developing end-to-end intelligent systems that continuously learn from their environment. I am fortunate to have worked with Yisong Yue and Anima Anandkumar at Caltech, and Pablo Moscato at the University of Newcastle.

Publications

Kevin Huang, Sahin Lale, Ugo Rosalia, Yuanyuan Shi, and Anima Anandkumar. CEM-GD: Cross Entropy Method with Gradient Descent for Model Based Reinforcement Learning, 2021. Submitted to Learning for Dynamics & Control (L4DC).
[paper] [code]

Pablo Moscato, Mohammad Nazmul Haque, Kevin Huang, Julia Sloan, and Jonathon Corrales de Olivera. Learning to extrapolate using continued fractions: Predicting the critical temperature of superconductor materials, 2021. Submitted to IEEE Transactions on Artificial Intelligence.
[paper]