Jens Tuyls

Computer Science PhD Student (5th year)

prof_pic.jpg

I am currently part of the Princeton NLP group, where I am advised by Professor Karthik Narasimhan. My research focuses on building decision-making agents, mainly using ideas from reinforcement learning (RL) and natural language processing (NLP). To this end, I also closely collaborate with Professor Benjamin Eysenbach as part of the Princeton RL Lab.

Specifically, my work has explored (1) how to build agents that can operate in textual environments, (2) how to leverage scaling laws developed in NLP for imitation learning agents, and (3) how to build agents that can explore their environments in a principled, self-supervised manner without any prior knowledge. Currently, I’m especially excited about building principled algorithms for grounding language and control.

Bio: I studied Computer Science and Engineering at UC Irvine, where I was fortunate to work with Professor Sameer Singh on interpretability in NLP, and with Professor Stephan Mandt and Professor Mike Pritchard on AI for climate. Now, I’m a 5th year PhD student in the Princeton NLP group.

news

Oct, 2024 Our work “Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning” was accepted to the IMOL workshop at NeurIPS.
Aug, 2024 Our work on language-guided world models was accepted for oral presentation at ACL SpLU-RoboNLP Workshop.
May, 2023 Completed internship at Amazon where I worked with Dhruv Madeka, Dean Foster, Kari Torkkola, and Sham Kakade on NetHack! Check out our work on “Scaling Laws for Imitation Learning in Single-Agent Games”.
Apr, 2022 Received NSF GRFP Honorable Mention!
Jan, 2022 Our paper on exploration in text-games was accepted as Spotlight at ICLR 2022!