35 Olden Street
My research spans the areas of natural language processing and reinforcement learning, with a view towards building intelligent agents that learn to operate in the world through both experience and existing human knowledge
I am looking for strong, motivated PhD students. If you are interested in joining our group, please apply directly to the graduate program in Princeton CS and mention me in your application (no emails please!). If you’re already a PhD student at Princeton, feel free to email me to setup a time to chat.
|Sep 2020||Check out our new papers to appear in EMNLP and NeurIPS 2020! Congrats to Shunyu, Rohan, Ameet, Jimmy, Raeid and Zhiwei!|
|Jul 2020||Here’s a recent talk I gave at the ICML LaReL workshop on how to scale up RL using language|
|Jan 2020||New paper on learning policies with safety constraints to appear in ICLR 2020. Congrats Jimmy!|
|Sep 2019||Two new papers: on calibrating language models (ICML 2020) and a novel algorithm for multi-objective RL (NeurIPS 2019).|
|May 2019||Check out my talk on task-agnostic priors for RL at the ICLR SPiRL workshop!|