Max Olan Smith

I am a Ph.D. candidate at the University of Michigan working with Michael P. Wellman. This summer I will be visiting DeepMind's Game Theory team in Paris working with Daniel Hennes. Previously, I was an intern with Aaron Courville at the Montréal Institute for Learning Algorithms. I am generally interested in multiagent learning, reinforcement learning, empirical game theory, 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

Co-Learning Empirical Games and World Models
Max Olan Smith, Michael P. Wellman
arXiv, 2023.
[pdf] [arxiv]
Strategic Knowledge Transfer
Max Olan Smith, Thomas Anthony, Michael P. Wellman
Journal of Machine Learning Research (JMLR), 2023.
[pdf] [html] [poster]
Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning
Marc Lanctot, John Schultz, Neil Burch, Max Olan Smith, Daniel Hennes, Thomas Anthony, Julien Perolat
Transactions of Machine Learning Research, 2023.
[pdf] [arXiv]
Learning to Play Against Any Mixture of Opponents
Max Olan Smith, Thomas Anthony, Michael P. Wellman
Frontiers in AI, 2023. (Originally appeared on arXiv in 2020).
Iterative Empirical Game Solving via Single Policy Best Response
Max Olan Smith, Thomas Anthony, Michael P. Wellman
International Conference on Learning Representations (ICLR), 2021. (Spotlight).
[pdf] [poster] [slides]
No Press Diplomacy: Modeling Multi-Agent Gameplay
Philip Paquette, Yuchen Lu, Steven Bocco, Max Olan Smith, Satya Ortiz-Gagne, Jonathan K. Kummerfeld, Satinder Singh, Joelle Pineau, Aaron Courville.
Advances in Neural Information Processing Systems (NeurIPS), 2019.
[pdf] [poster] [code]
Speaker Naming in Movies
Mahmoud Azab, Mingzhe Wang, Max Olan Smith, Moriyuki Kojima, Jia Deng, and Rada Mihalcea.
North American Chapter of the Association for Computational Linguistics (NAACL), 2018.
Long Term Effects of Pair Programming
Max Olan Smith, Andrew Giugliano, and Andrew DeOrio.
IEEE Transactions on Education, 2017.
[pdf] [slides]
A Unified Framework for Automatic Wound Segmentation and Analysis with Deep Convolutional Neural Networks
Changhan Wang, Xinchen Yan, Max Olan Smith, Kanika Kochhar, Marcie Rubin, Stephen M. Warren, James Wrobel, and Honglak Lee.
IEEE Engineering in Medicine and Biology (EMBC), 2015.