My research interests are quite broad, one of my broad goals is to build machine learning methods and algorithms, as well as to bring principled scientific values to AI and machine learning research.

I am most interested in applications of machine learning to science and language.

Currently I am mostly working on reinforcement learning and on offline reinforcement learning for the positive real-world-impact.

I believe reinforcement learning is a crucial concept to build intelligent agents that can interact with the world and build a representation of

Please feel free to drop me an email if you have research related questions or thoughts.

For my full list of publications, please check my Google Scholar page. Hopefully, that will give you a good idea of the types of subjects that I am most interested in.



Some Selected Publications