William Dudley
Doctoral Student at Imperial College London
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolWilliam Dudley is a doctoral student at Imperial College London with a decade of experience at the intersection of biomechanics, reinforcement learning, and human-robot interaction. He researches dexterous motion in humans and hierarchical reinforcement learners, bringing rigorous mathematical training (First Class Maths BSc, MSc with Distinction in Biomedical Engineering) to complex control problems. Practically minded, he contributes to open-source RL tooling—refactoring PettingZoo's rendering to a Pygame-based system to improve multi-agent visualization and usability. Based in London, he combines academic depth with full-stack development chops and a knack for translating theoretical insights into practical simulation and interaction improvements.
10 years of coding experience
Master of Science - MS, Biomedical/Medical Engineering, Distinction, Master of Science - MS, Biomedical/Medical Engineering, Distinction at Imperial College LondonMathematics, Physics, Business Studies, Mathematics, Physics, Business Studies at Peter SymondsGCSEs, GCSEs at Kings' School WinchesterBSc with a year abroad, Mathematics, First class honours, BSc with a year abroad, Mathematics, First class honours at Cardiff University / Prifysgol CaerdyddMathematics, Mathematics at The University of British Columbia
English
Github Skills (5)
gymnasium10
pygame10
python10
multi-agent-reinforcement-learning9
api9
Programming languages (8)
Github contributions (5)
Farama-Foundation/PettingZoo
Jun 2022 - Jan 2023
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:4 releases, 36 reviews, 90 commits in 6 months
Contributions summary:William primarily focused on refactoring the rendering system of the pettingzoo environment. They replaced the existing rendering.py with a Pygame-based implementation, which involved initializing the screen, handling display updates, and integrating agent positions and visual elements. This shift aimed to deprecate the original rendering approach, suggesting an effort to optimize or streamline the environment's visual output using a more common graphics library. Additionally, the user implemented text overlays for the agents to further enhance the visualization.
multi-agent-reinforcement-learningapigymnasiumreinforcement-learningmultiagent-reinforcement-learning
Farama-Foundation/Minari
Oct 2022 - Jan 2023
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
Contributions:1 release, 1 review, 196 commits in 2 months
reinforcement-learningdatasetsgymnasiumoffline-rl
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.