Samuel Sokota

Logo

I am a PhD student in the Machine Learning Department at Carnegie Mellon University supervised by Zico Kolter. Previously, I did my master’s at the University of Alberta, where I worked with Marc Lanctot and Martha White. Before that, I did my undergraduate at Swarthmore College, where I played lacrosse, studied mathematics and physics, and worked with Bryce Wiedenbeck.

The best way to reach me is at ssokota(at)andrew(dot)cmu(dot)edu.

Publications

Computing Low-Entropy Couplings for Large-Support Distributions
Samuel Sokota, Dylan Sam, Christian Schroeder de Witt, Spencer Compton, Jakob Foerster, J. Zico Kolter
UAI 2024
Paper    Thread    Code   

The Update-Equivalence Framework for Decision-Time Planning
Samuel Sokota, Gabriele Farina, David J. Wu, Hengyuan Hu, Kevin A. Wang, J. Zico Kolter, Noam Brown
ICLR 2024
Paper    Thread   

Neural Functional Transformers
Allan Zhou, Kaien Yang, Yiding Jiang, Kaylee Burns, Winnie Xu, Samuel Sokota, J. Zico Kolter, Chelsea Finn
NeurIPS 2023
Paper    Code   

Permutation Equivariant Neural Functionals
Allan Zhou, Kaien Yang, Kaylee Burns, Yiding Jiang, Samuel Sokota, J. Zico Kolter, Chelsea Finn
NeurIPS 2023
Paper    Thread    Code   

Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
Samuel Sokota, Ryan D’Orazio, Chun Kai Ling, David J. Wu, J. Zico Kolter, Noam Brown
ICML 2023
Paper    Thread   

Learning Intuitive Policies Using Action Features
Mingwei Ma*, Jizhou Liu*, Samuel Sokota*, Max Kleiman-Weiner, Jakob Foerster
ICML 2023
Paper    Thread   

A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Samuel Sokota*, Ryan D’Orazio*, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer
ICLR 2023
Paper    Thread    Talk    Sequence-Form Code    Behavioral-Form Code   

Perfectly Secure Steganography Using Minimum-Entropy Coupling
Christian Schroeder de Witt*, Samuel Sokota*, J. Zico Kolter, Jakob Foerster, Martin Strohmeier
ICLR 2023
Paper    Original Code    Updated Code   

Communicating via Markov Decision Processes
Samuel Sokota*, Christian Schroeder de Witt*, Maximilian Igl, Luisa Zintgraf, Philip Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob Foerster
ICML 2022
Paper    Code   

A Fine-Tuning Approach to Belief State Modeling
Samuel Sokota, Hengyuan Hu, David J. Wu, J. Zico Kolter, Jakob Foerster, Noam Brown
ICLR 2022
Paper   

Monte Carlo Tree Search with Iteratively Refining State Abstractions
Samuel Sokota, Caleb Ho, Zaheen Amhad, J. Zico Kolter
NeurIPS 2021
Paper   

Solving Common-Payoff Games with Approximate Policy Iteration
Samuel Sokota*, Edward Lockhart*, Finbarr Timbers, Elnaz Davoodi, Ryan D’Orazio, Neil Burch, Martin Schmid, Michael Bowling, Marc Lanctot
AAAI 2021
Paper    Thesis    Capi Code    Tiny Hanabi Code   

Selective Dyna-Style Planning Under Limited Model Capacity
Zaheer Abbas, Samuel Sokota, Erin J. Talvitie, Martha White
ICML 2020
Paper   

Simultaneous Prediction Intervals for Patient-Specific Survival Curves
Samuel Sokota*, Ryan D’Orazio*, Khurram Javed, Humza Haider, Russell Greiner
IJCAI 2019
Paper    Code   

Learning Deviation Payoffs in Simulation-Based Games
Samuel Sokota, Caleb Ho, Bryce Wiedenbeck
AAAI 2019
Paper