Dustin Morrill
Research Scientist at University of Alberta
Edmonton, Alberta, Canada
Summary
👤
Senior🎓
Top SchoolDustin Morrill is a research scientist based in Edmonton with 14 years of experience at the intersection of algorithmic game theory and reinforcement learning, currently conducting research at SonyAI. He has a strong academic foundation from the University of Alberta, progressing from undergraduate projects in computer poker to a master’s-level graduate research role and sustained teaching responsibilities. Dustin contributes to notable open-source projects like DeepMind’s OpenSpiel, improving robustness, memory safety, and game logic—work that supports reproducible RL and game-playing research. His background includes building full projects (an ACPC Poker GUI Client) and low-level C/C++ systems for UAV control, showing comfort across research code and production-grade systems. He combines hands-on development, teaching, and publication-oriented research, and he has a track record of finding subtle correctness and integration issues that improve long-lived codebases.
14 years of coding experience
9 years of employment as a software developer
Master’s Degree, Computer Science, Master’s Degree, Computer Science at University of Alberta
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
python10
reinforcement-learning10
videogames9
cprogramming-language9
c-language9
coregames9
algorithms9
multi-agent8
tensorflow7
Programming languages (6)
Github contributions (5)
google-deepmind/open_spiel
Aug 2019 - May 2020
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:9 commits, 7 PRs, 10 comments in 8 months
Contributions summary:Dustin primarily focused on improving the robustness and correctness of the OpenSpiel library. They addressed potential errors related to memory management, specifically by modifying the import order of libraries within the Python code. The user also implemented algorithmic improvements to the reservoir sampling data structure and enhanced the game logic by adding checks for simultaneous move games. Furthermore, the user updated the codebase to avoid deprecation warnings and ensure the project compiles correctly.
cppmultiagentgamespythondatamining
dmorrill10/open_spiel
Aug 2019 - Aug 2024
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Contributions:27 pushes, 10 branches in 5 years
gamesreinforcement-learningplanningreinforcementenvironments
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.