I am a final-year undergraduate studying mathematics and computer science at Caltech where I am fortunate to be advised by Anima Anandkumar and Jacob Steinhardt.

I am interested in trustworthy and reliable machine learning through greater alignment with human values and stronger adversarial robustness.

See here for my CV. Feel free to email me at aypan [at] caltech [dot] edu.


The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
Alexander Pan, Kush Bhatia, Jacob Steinhardt
NeurIPS Deep RL Workshop 2021. Under submission at ICLR 2022.
pdf / code

Improving Robustness of RL for Power System Control with Adversarial Training
Alexander Pan, Yongkyun (Daniel) Lee, Huan Zhang, Yize Chen, Yuanyuan Shi
ICML RL4RL Workshop 2021. Under submission at PSCC 2022.
pdf / code

Opinion Formation on Networks
Alexander Pan, Heather Z. Brooks, Franca Hoffmann, Mason A. Porter
Technical Report.


I enjoy teaching and am committed to promoting access to math and CS at all levels.

Caltech Y RISE
Volunteer Tutor: 2018 - Present

Caltech CS 21: Complexity Theory
Teaching Assistant: Winter 2020


I have been fortunate to work on some interesting hackathon projects with Yongkyun (Daniel) Lee and Evan Yeh.

Best social network hack - Stanford Hackathon 2021
chrome extension / code

homES ReInvented
Best use of ESRI technology - Caltech Hackathon 2020