Samuel Sokota

Logo

I am a researcher at OpenAI.

I did my PhD with Zico Kolter in the Machine Learning Department at Carnegie Mellon University, and before that a master’s at the University of Alberta. My academic research focused on reinforcement learning and test-time compute, especially under imperfect information.

I did my undergraduate at Swarthmore College, where I studied mathematics and physics and played lacrosse.

The best way to reach me is ssokota(at)openai(dot)com.

Selected Research

Scalable decision-making for games of imperfect information
Samuel Sokota, Eugene Vinitsky, Hengyuan Hu, Zhiyuan Fan, J. Zico Kolter, Gabriele Farina
Nature 2026
Paper    Code   

Reevaluating Policy Gradient Methods for Imperfect-Information Games
Max Rudolph*, Nathan Lichtle*, Sobhan Mohammadpour*, Alexandre Bayen, J. Zico Kolter, Amy Zhang, Gabriele Farina, Eugene Vinitsky, Samuel Sokota
ICLR 2026
Paper    Thread    Exploitability Package    Code    Games Demo   

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   

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   

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