Sophie Broderick
About Me
Princeton CS 2027 | Safe and Robust RL | Skill Learning
Research @ Reinforcement Learning Lab
I’m an undergraduate student at Princeton excited about AI. Let’s talk about research or ideas for making adaptive intelligent systems that align with humanity.
I also create art and write humor focused on the tech world, AI, and the tension between humans and machines.
Selected Research
Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach. (Not published yet)
This project evaluates the robustness of Maximum Entropy Reinforcement Learning (MaxEnt RL) via Energy-Based Normalizing Flows (EBFlow). While RL algorithms are typically tested in clean, idealized simulations, this work introduces realistic disturbances—including sensor corruption, action noise, and observation noise—using tools from the Robust Gym benchmark to assess generalization.
Compose SQL in a new way. Instead of writing text, just select which columns you want to see. Create joins by drilling down into linked tables.
Contributed to the Infinigen project: an open source procedural generator of 3D environments optimized for AI research. Created adaptive randomized textures with unlimited variations while ensuring accurate 3D ground truth.
Selected Writings
In the beginning, there was the Model.
And the Model was without form.
And darkness was upon the face of the training data...
Published July 29, 2025
Art
Intimate Machines
Interactive Art
Four Types of AI
Portraits
