Ryan Sullivan
Postdoctoral Research Fellow at The University of British Columbia
College Park, Maryland, United States
Summary
🤩
Rockstar🎓
Top SchoolRyan Sullivan is a postdoctoral researcher and RL practitioner with 11 years of hands-on experience building open-ended learning systems, policy-gradient analyses, and automatic curriculum methods. He completed a PhD at the University of Maryland, contributed as a core developer to the widely used PettingZoo multi-agent RL library, and maintains open-source tooling such as the Syllabus curriculum library. His industry internships at Google Research, Amazon Science, and Sony AI focused on RL, RLHF, and productionizing experiments—work that yielded publications at EMNLP and AAAI and concrete training-speed improvements. Now at UBC with Jeff Clune, he explores intersections between LLMs and RL, aiming to use language models to scaffold curricula and boost agent generality. He pairs deep empirical rigor with product-minded engineering, from responsive documentation UIs to refactoring complex environments like checkers for correctness and robustness.
11 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of MarylandBachelor of Science (B.S.) Computer Science Honors and Statistics, Bachelor of Science (B.S.) Computer Science Honors and Statistics at Purdue University
English, Spanish
Stackoverflow
307reputation
4kreached
7answers
0questions
Github Skills (16)
game-development10
pygame10
python10
multi-agent-reinforcement-learning9
gymnasium9
api8
api-design8
front-end-development8
webgl6
ios6
cocoa-touch6
browser6
swift6
javascript6
annotations6
Programming languages (6)
Github contributions (5)
Farama-Foundation/PettingZoo
Aug 2020 - Apr 2022
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:61 reviews, 178 commits, 15 PRs in 1 year 8 months
Contributions summary:Ryan contributed primarily to improving the UI and functionality of the documentation and the checkers environment. They updated the styling and layout of the documentation, focusing on responsiveness for different screen sizes. In addition, they refactored the checkers environment, modifying the action space, observation space, and core logic to resolve implementation errors and improve overall game behavior.
agentreinforcement-learningreinforcement-learning-agentgymnasiumdeep-reinforcement-learning
FlyingStrainer/notebook-webclient
Sep 2017 - Jan 2019
Contributions:12 PRs, 67 pushes, 7 branches in 1 year 3 months
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.