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.
News
Apr 2024: Gave an invited talk on Human-Regularized PPO at the Berkeley Multiagent Learning Seminar! The slides are here.
Sep 2023: Started my Ph.D. at NYU with the EMERGE Lab!
Papers
Human-compatible driving partners through data-regularized self-play reinforcement learning
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