Daphne Cornelisse

Hello! I am a first-year Ph.D. student at NYU, advised by Professor Eugene Vinitsky. My current research is focused on building competent and human-compatible agents, with applications to autonomous vehicles. To this end, I incorporate human data and learning principles in multi-agent settings, focusing on enabling agents to plan under uncertainty and anticipate the actions of others

I have a broad interest in mixed/cooperative multi-agent games and the factors contributing to effective teams. How do the reasoning abilities of individual agents contribute to the success of the team as a whole? How can a group of individuals form a team that exceeds the capabilities of the sum of their parts?

Outside the lab, I enjoy boxing, going for a run along the East River, reading, and sketching.


Google Scholar / Twitter / Goodreads

News 

Papers 

Human-compatible driving partners through data-regularized self-play reinforcement learning

Daphne Cornelisse, Eugene Vinitsky

ArXiv preprint, 2024


Paper | Tweet | Project page | Code | Slides

Neural payoff machines: predicting fair and stable payoff allocations among team members 

Daphne Cornelisse, Thomas Rood, Mateusz Malinowski, Yoram Bachrach, Tal Kachman

NeurIPS 2022

Paper | Poster | Video | Tweet | Master thesis

Selected talks  

An introduction to equilibrium computation in multi-agent settings

Computational Statistics course at Columbia (auditing), New York City, Dec 2021

Slides