Emma Jordan is a teaching professor in the Department of Computer Science at the University of Pittsburgh. She received her PhD from the University of Massachusetts Amherst, advised by Phil Thomas, and completed a postdoc at the University of Alberta under Martha White and Adam White. Her research addresses fundamental problems in reinforcement learning and AI more broadly, with a parallel line of work examining the experimental practices of the AI research community — she is an advocate for greater scientific rigor in how the field evaluates its own claims. In the classroom, she teaches courses including Deep Learning and Reinforcement Learning, with a consistent emphasis on building students' foundational understanding rather than surface-level familiarity with tools.
Education & Training
- PhD, University of Massachusetts Amherst
Evaluating the performance of reinforcement learning algorithms
E Jordan, Y Chandak, D Cohen, M Zhang, P Thomas - International Conference on Machine Learning, 2020
The Cliff of Overcommitment with Policy Gradient Step Sizes
E Jordan, S Neumann, JE Kostas, A White, PS Thomas - Reinforcement Learning Conference, 2024
Behavior alignment via reward function optimization
D Gupta, Y Chandak, E Jordan, PS Thomas… - Advances in Neural Information Processing Systems, 2023
reinforcement learning
