Suvansh Sanjeev

I am a researcher at OpenAI, where I work on the Applications Research Team. I have worked on our early robotics efforts, and more recently on enhancing the performance of our reasoning models outside the canonical domains of math and coding.

I was previously on leave from my PhD at the Robotics Institute at Carnegie Mellon University, where I was advised by Zico Kolter and Zac Manchester. I graduated from UC Berkeley, where I worked with Professors Sergey Levine and Claire Tomlin in the Berkeley Artificial Intelligence Research (BAIR) Lab on deep RL and safe learning.

 /   /   /   / 

Last year, I worked on Brilliantly, making open-source AI projects and providing custom AI solutions for clients. You can learn about the projects Brilliantly worked on here.

My past research worked towards bringing reinforcement learning to the real world. Most recently, I worked on gray-box methods for control of quadrotors. I have also worked on developing more natural means of task specification for deep RL to avoid the burden of manually engineered reward functions, as well as on developing data-efficient learning techniques that allow for safety guarantees throughout the learning process.

Website template