Audrey Huang

I am a Computer Science PhD student at UIUC, where I am fortunate to be advised by Nan Jiang. I work on reinforcement learning and, more broadly, interactive decision making.

I'm thankful for incredible summers at Microsoft Research working with Akshay Krishnamurthy and Dylan Foster; at Google Research with Mohammad Ghavamzadeh and Marek Petrik; and at Adobe Research.

[google scholar]     [email]

I care about developing principled and implementable algorithms with provable guarantees. Current/previous threads include:

• Online finetuning (e.g., of large language models)
• Imitation learning
• Tractable online exploration
• Offline RL and evaluation

I believe that theoretical insights into fundamental questions will lead to real-world algorithmic improvements, and vice versa.