Previously, I spent two years as a software engineer at Waymo, working on bringing autonomous vehicles to market. Prior to that, I was studying Computer Science at Princeton (‘16), and graduated with certificates in Applied & Computational Math and Robotics & Intelligent Systems.
I’m a big fan of running, discovering stories (through books, people, or otherwise), appreciating art, and finding ways to engage with my local community.
My interests lie at the intersection of machine learning and human-AI interaction. You'll hear me talk about this as human-in-the-loop learning.
I want to understand how we can build intelligent systems that better accomodate people over repeated interactions.
- How can we truly understand what a person likes and dislikes, wants and wants to avoid?
- How can we navigate the reality that people are non-stationary and evolving?
- What interaction mechanisms can we use to get more valuable information from people?
- How do we ensure that these systems can learn from people with a variety of capabilities?
I am also interested in the ethical implications of this line of research, and have been learning more about product design and tech policy.
Publications(*) denotes authors who contributed equally
Interaction Considerations in Learning from Humans. Pallavi Koppol, Henny Admoni, Reid Simmons. Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI) 2021.
Understanding the Relationship between Interactions and Outcomes in Human-in-the-Loop Machine Learning. Yuchen Cui*, Pallavi Koppol*, Henny Admoni, Scoot Niekum, Reid Simmons, Aaron Steinfeld, Tesca Fitzgerald. Proceedings of the 30th International Joint Conference on Aritificial Intelligence (IJCAI) 2021.
Iterative Interactive Reward Learning. Pallavi Koppol, Henny Admoni, Reid Simmons. Participatory Approaches to Machine Learning Workshop at ICML 2020.