I’m a 4th year PhD student at the University of Maryland studying reinforcement learning in a variety of contexts. My research centers around developing an empirical understanding of policy gradient methods and developing automatic curriculum learning methods. I was one of the developers of PettingZoo for multiagent environments and have worked on a number of open source tools for RL, including my curriculum learning library Syllabus. I’ve interned at Amazon Science and Google Research researching multi-objective RL and RLHF. I’m very interested in open-ended learning, automatic curriculum learning, and new directions combining LLMs with reinforcement learning. Feel free to reach out if you’d like to discuss ideas or opportunities to collaborate! I’m also looking for internships for Spring and Summer 2024.
Download my resumé.
PhD in Computer Science, Expected 2025
University of Maryland
BSc in Computer Science, 2020
BSc in Applied Statistics, 2020
BSc in Mathematics, 2020
We applied the implementation tricks introduced by DreamerV3 to PPO, and identified cases where they help or harm reward robustness.
The paper describes Neural MMO 2.0, a massive multitask update for the multiagent NeuralMMO environment.
We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with PPO.
We developed a new visualization technique for reinforcement learning and used it to demonstrate a failure mode of policy gradient methods.