I am a PhD candidate at the University of Texas at Austin, where I conduct research on deep reinforcement learning, state representation learning, and physics-informed AI. I am currently working out of the Computational Visualization Center (CVC Lab), where I am advised by Chandrajit Bajaj and Eric Bickel.

My research focuses on applying machine learning techniques to complex systems, with a particular emphasis on reinforcement learning and state representation learning. I have previously completed a three-year fellowship with Equinor, where I worked on applying these techniques to reservoir engineering.

In my research, I use deep reinforcement learning to train agents to make decisions in complex environments by rewarding them for actions that lead to desirable outcomes. I also use state representation learning to automatically discover the underlying structure of complex systems and improve the performance of reinforcement learning agents. Additionally, I incorporate physical constraints and prior knowledge about the behavior of physical systems into my machine learning models using physics-informed AI, which can improve their accuracy and robustness.

My research aims to advance the field of machine learning and apply it to real-world problems in a range of fields.

You can learn more about my professional background and connect with me on LinkedIn, or visit my personal website.