Arthur Allshire
Graduate Student
Berkeley, California, United States
Summary
👤
SeniorArthur Allshire is a graduate student and robotics researcher based in Berkeley with 11 years of hands-on experience at the intersection of robotics, machine learning, and computer vision. He has driven GPU-accelerated sim2real work and in-hand manipulation research through multiple roles at NVIDIA and Berkeley AI Research, and collaborated with ETH Zürich on robotic systems. Arthur contributes practical reinforcement learning fixes and features to open-source RL projects (e.g., improving multi-GPU support and recurrent observation handling in rl_games), reflecting a blend of research rigor and production-minded engineering. His background spans cloud ML systems, autonomous vehicle stacks, and founding a public-health tech nonprofit—evidence of both technical depth and applied impact in real-world settings.
11 years of coding experience
7 years of employment as a software developer
Github Skills (10)
mask-rcnn10
faster-rcnn10
pytorch10
deep-learning10
python10
reinforcement-learning10
n9
rnn-model9
multiple-gpu8
multi-gpu8
Programming languages (8)
Github contributions (5)
Denys88/rl_games
Dec 2020 - Jul 2022
RL implementations
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 8 commits, 13 PRs in 1 year 8 months
Contributions summary:Arthur contributed to the reinforcement learning implementations within the repository by fixing bugs and adding new functionalities. Their work included supporting different convolutional neural network configurations, resolving multi-head value calculation issues, and addressing compatibility with dictionary-based observations for recurrent neural networks. They also added an option to disable the vector environment and fixed issues related to multi-GPU and single-GPU training setups.
pytorchimplementationsdeep-learningreinforcement-learninggymnasium
ArthurAllshire/rl_games
Nov 2020 - Jul 2023
RL implementations
Contributions:35 pushes, 14 branches in 2 years 8 months
pytorchimplementationsreinforcement-learningdeep-reinforcement-learning
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.