About me
Hey folks! I’m a PhD student at UC Irvine advised by Prof. Roy Fox. I’m interested in developing sample efficient and scalable reinforcement learning (RL) algorithms. More specifically, I design offline RL and maximum-entropy RL algorithms from first principles to enable sample-efficient robot learning. I’m also increasingly interested in pre-training generalist policies and leveraging world models for physical intelligence.
News
- Jun 2026 Returned to Amazon as an Applied Scientist Intern for the summer.
- 2026 REG: In-Sample RL via Regularizing the Evaluation Gap accepted at ICML 2026.
- 2026 Differentially Private Non-Convex Learning: From GLMs to Multi-Layer Neural Networks accepted at AAMAS 2026.
- Jun 2025 Joined Amazon as an Applied Scientist Intern for the summer.
Publications
- REG: In-Sample RL via Regularizing the Evaluation Gap
- Differentially Private Non-Convex Learning: From Generalized Linear Models to Multi-Layer Neural Networks
All publications → · Google Scholar ↗