Scott Emmons

  • Program Year: 4
  • Academic Institution: University of California, Berkeley
  • Field of Study: Computer Science
  • Academic Advisor: Stuart Russell
  • Practicum(s):
    Argonne National Laboratory (2021)
  • Degree(s):
    B.S. Mathematics, and B.A. Computer Science, University of North Carolina at Chapel Hill, 2019
  • Personal URL: http://scottemmons.com/

Summary of Research

In addition to creating new algorithms, Scott has aspired to connect algorithms’ underlying mathematics and computer science to the goals of their users. His research on unsupervised learning in network science and artificial intelligence in robotics has studied how to measure, compare, and post-process the results of community detection algorithms; how to visualize massively open online course data for its relevant users; and how to guide algorithms’ optimization with desired user properties.

Publications

Scott Emmons, Caspar Oesterheld, Andrew Critch, Vince Conitzer, & Stuart Russell: "For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria." International Conference on Machine Learning, 2022.

Scott Emmons, Benjamin Eysenbach, Ilya Kostrikov, & Sergey Levine: "RvS: What is Essential for Offline RL via Supervised Learning?" International Conference on Learning Representations, 2022.

Xin Chen*, Sam Toyer*, Cody Wild*, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H. Wang, Ping Luo, Stuart Russell, Pieter Abbeel, & Rohin Shah: "An Empirical Investigation of Representation Learning for Imitation." Neural Information Processing Systems (NeurIPS), 2021.

Scott Emmons*, Ajay Jain*, Michael Laskin*, Thanard Kurutach, Pieter Abbeel, & Deepak Pathak: "Sparse Graphical Memory for Robust Planning." Neural Information Processing Systems (NeurIPS), 2020.

Eun Lee, Scott Emmons, Ryan Gibson, James Moody, & Peter J. Mucha: "Concurrency and Reachability in Treelike Temporal Networks." Physical Review E, 2019.

Scott Emmons & Peter J. Mucha: "A Map Equation with Metadata: Varying the Role of Attributes in Community Detection." Physical Review E, 2019.

Kris Hauser & Scott Emmons: "Global Redundancy Resolution via Continuous Pseudoinversion of the Forward Kinematic Map." IEEE Transactions on Automation Science and Engineering, 2018.

Scott Emmons, Robert Light, & Katy Borner: "MOOC Visual Analytics: Empowering Students, Teachers, Researchers, and Platform Developers of Massively Open Online Courses." Journal of the Association for Information Science and Technology (JASIST), 2017.

William H. Weir, Scott Emmons, Ryan Gibson, Dane Taylor, & Peter J. Mucha: "Post-Processing Partitions to Identify Domains of Modularity Optimization." Algorithms, 2017.

Scott Emmons, Mike Gallant, Stephen Kobourov, & Katy Borner: "Analysis of Network Clustering Algorithms and Cluster Quality Metrics at Scale." PLoS ONE, 2016.

Awards

Robertson Scholars Leadership Program ($250,000). 2015 - 2019.
- Highly selective undergraduate merit scholarship providing unique dual citizenship at UNC and Duke.

Goldwater Scholar ($15,000). 2017 - 2019.
- Awarded to 300 students in the U.S. per year for natural sciences, mathematics, and engineering research.

Archibald Henderson Medal. 2019.
- "A gold medal given annually to the undergraduate judged by [UNC's] Department of Mathematics to have demonstrated a high degree of mathematical ability and the greatest promise of originality in the field."

Alfred Brauer Prize. 2018.
- Annual award granted by UNC's Department of Mathematics "to the undergraduate who has demonstrated the greatest ability and promise for achievement in the fields of algebra or number theory."