Max Olan Smith

I am a fourth year Ph.D. student at the University of Michigan working with Michael P. Wellman. Previously I was an intern with Aaron Courville at the Montréal Institute for Learning Algorithms. I am interested in multiagent learning, reinforcement learning, continual learning, meta-learning, deep learning, and education.

As an undergraduate I had the absolute pleasure to work with many brilliant advisors: Honglak Lee, Rada Mihalcea, and Andrew DeOrio. I also spent my summers at Google and Sandia National Labs.

Email  /  CV  /  Google Scholar

Research
Iterative Empirical Game Solving via Single Policy Best Response
Max O. Smith, Thomas Anthony, Michael P. Wellman
ICLR, 2021. (Spotlight)
[paper] [slides]
Learning to Play Against Any Mixture of Opponents
Max O. Smith, Thomas Anthony, Yongzhao Wang, Michael P. Wellman
ArXiv, 2020.
[paper]
No Press Diplomacy: Modeling Multi-Agent Gameplay
Philip Paquette, Yuchen Lu, Steven Bocco, Max O. Smith, Satya Ortiz-Gagne, Jonathan K. Kummerfeld, Satinder Singh, Joelle Pineau, Aaron Courville.
NeurIPS, 2019.
[paper] [poster]
Speaker Naming in Movies
Mahmoud Azab, Mingzhe Wang, Max O. Smith, Moriyuki Kojima, Jia Deng, and Rada Mihalcea.
NAACL, 2018.
[paper]
Long Term Effects of Pair Programming
Max O. Smith, Andrew Giugliano, and Andrew DeOrio.
IEEE Transactions on Education, 2017.
[paper] [slides]
A Unified Framework for Automatic Wound Segmentation and Analysis with Deep Convolutional Neural Networks
Changhan Wang, Xinchen Yan, Max O. Smith, Kanika Kochhar, Marcie Rubin, Stephen M. Warren, James Wrobel, and Honglak Lee.
IEEE Engineering in Medicine and Biology (EMBC), 2015.
[paper]

Last Updated: 2021-03-06 Website designed by Jon Barron