Benjamin Liu
Visiting Researcher at University of Washington
Singapore, Singapore
Summary
🤩
Rockstar🎓
Top SchoolBenjamin Liu is a PhD student in Computer Science at the National University of Singapore focused on reinforcement learning, reasoning, and ML systems for real-world decision-making. With five years of industry experience including stints at Microsoft and Facebook Research, he builds high-performance, production-oriented RL components and environments. His open-source contributions to EnvPool—adding Mujoco and DeepMind Control Suite environments—highlight his backend systems skills and understanding of vectorized, parallel environment execution. Benjamin combines academic rigor from NUS and Peking University with practical engineering that bridges research prototypes and scalable tooling for autonomous agents. Notably, he tends to focus on core environment logic and performance-sensitive integrations that enable faster RL experimentation and deployment.
6 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at National University of SingaporeBachelor of Science - BS Computer Science, Bachelor of Science - BS Computer Science at Peking UniversityDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Stanford University
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
environmental10
mujoco10
dev-environment10
c-language10
cprogramming-language10
environ10
reinforcement-learning10
enviroment10
python9
cpp6
robotics5
Programming languages (5)
Github contributions (5)
sail-sg/envpool
Apr 2022 - Oct 2022
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:18 reviews, 15 commits, 19 PRs in 6 months
Contributions summary:Benjamin primarily focused on adding new reinforcement learning environments to the EnvPool project, specifically integrating Mujoco environments. Their work involved creating new environment classes like InvertedDoublePendulumEnv and Walker2dEnv, defining their configurations, and integrating them into the overall EnvPool framework. The commits demonstrate the implementation of core environment logic, observation and action space definitions, and reward calculations, expanding the capabilities of the environment execution engine. The user also added the dmc Hopper, Ball in cup, Acrobot, Fish, Humanoid, Cartpole, and Swimmer environments.
rl-environmentreinforcement-learningparallel-processingcpp17reinforcement-learning-environments
Benjamin-eecs/torchopt
Apr 2022 - Aug 2023
Contributions:416 pushes, 64 branches in 1 year 4 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.