Ashvin Nair
RL Foundations
Berkeley, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAshvin Nair is an RL-focused research engineer with 13 years of experience blending academic depth and production ML work, currently leading RL Foundations at Cursor after three years as a Member of Technical Staff at OpenAI. A UC Berkeley PhD student and long-time Robot Learning Lab researcher, he has deep expertise in offline and online reinforcement learning, contributing implementations like AWAC and IQL to the widely used rlkit repository. His background spans research internships at OpenAI and Facebook and hands-on engineering roles that bridge dataset integration, algorithm refinement, and practical examples for continuous control. Based in Berkeley, he pairs rigorous academic training with a pragmatic engineering approach, often surfacing subtle robustness and terminal-handling improvements that make RL codebases easier to use in real experiments.
13 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy - PhD EECS, Doctor of Philosophy - PhD EECS at University of California, BerkeleyWinchester High
Malayalam
Stackoverflow
791reputation
79kreached
36answers
4questions
Github Skills (14)
algorithm10
pytorch10
machine-learning10
sac10
machine-learning-algorithms10
deep-learning10
python10
reinforcement-learning10
gymnasium9
openai-gym9
arraylist6
syntaxerror6
sorting6
java6
Programming languages (5)
Github contributions (5)
rail-berkeley/rlkit
Jun 2019 - Oct 2021
Collection of reinforcement learning algorithms
Role in this project:
ML Engineer
ML EngineerContributions:1 review, 17 commits, 8 PRs in 2 years 5 months
Contributions summary:Ashvin implemented and refined reinforcement learning algorithms within the RLkit framework. Their contributions include adding an AWAC implementation and examples, specifically modifying code related to the core RL components. The user also worked on IQL implementation and examples, demonstrating a focus on offline reinforcement learning and dataset integration. Furthermore, they made minor changes to terminal handling and added a simple continuous classical control example.
reinforcement-learning-algorithmsactor-criticddpgreinforcement-learningdeep-reinforcement-learning
anair13/rlkit
Feb 2019 - Oct 2021
Collection of reinforcement learning algorithms
Contributions:50 commits, 1 PR, 43 pushes in 2 years 7 months
reinforcement-learning-algorithmsreinforcement-learningdeep-reinforcement-learningmachine-learninglearning-algorithms
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.