This summer CHAI members virtually mentored eight interns. CHAI interns develop essential research skills in the fields of machine learning and AI safety, preparing them for graduate school and industry opportunities.
Cynthia Chen, an undergrad from University of Hong Kong, was mentored by Sam and Scott, and they were working on using tools in causality to assist ML with a focus on imitation learning.
- Eric Michaud, an undergrad at UC Berkeley, was mentored by Adam, and they were working on reward model interpretability.
- Stephen Casper, an undergrad at Harvard University, was mentored by Daniel, and they were working on clustering/modularity.
- Charlotte Roman, PhD student at University of Warwick (UK), was mentored by Michael, and they were working on detecting and defending against policy exploitation in MARL.
- Harry Giles, a maths graduate who spent a few years working in finance, was mentored by Lawrence. They were looking at theoretical justifications of modeling human behavior on Boltzmann rationality in discrete and continuous cases.
- Johannes Treutlein, an incoming MSc in CS student at University of Toronto (formerly at Technical University of Berlin), was mentored by Michael and Jakob Foerster. They were working on multi-agent RL.
- Michael McDonald, incoming M.S. student at UC Berkeley and former undergrad at UC Berkeley, was mentored by Dylan, and they were working on imitation learning for multi-goal tasks.
- Sergei Volodin, a Master student at the Swiss Federal Institute of Technology in Lausanne (EPFL) studying Computer Science and Neuroscience was mentored by Adam. They were working on defenses for adversarial policies.