Sophie Broderick — AI & Reinforcement Learning Researcher

About Me

Princeton CS 2027 | Reinforcement Learning, LLMs, Semantic Representations, Diversity
Research @ Reinforcement Learning Lab

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.

LLM RL Post-Training

Large Language Models often converge to a narrow set of high-probability ideas. This research investigates methods to mitigate this tendency via reinforcement learning.
ICML 2026 | Learning to Perceive the World Through Control: Empowerment-Based Representation Learning.

Empowerment—an objective that measures how much influence an agent has over its environment—provides a principled way to learn concise representations that capture only the aspects of the environment that matter for control while ignoring irrelevant distractors.

Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach
Evaluating Robustness of MEow RL Under Real-World Noisy Conditions

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.

Infinigen

Built a working prototype for procedural texture generation in Blender/Python, creating adaptive randomized textures with effectively unlimited variation for synthetic 3D environments while preserving accurate ground truth. Applied best practices for source code management, version control, and collaborative development in GitHub.

Contract Writer, Chronicle Books — Authored the full text of a technology humor book, scheduled for publication in Spring 2027
Tech satire published in McSweeney’s Internet Tendency