Yan (Rocky) Duan

I'm building intelligent softwares and algorithms for robots at covariant.ai (formerly Embodied Intelligence).

I obtained my PhD degree from UC Berkeley, advised by Pieter Abbeel. My thesis is Meta Learning for Control.

Previously, I also worked at OpenAI as a research scientist.

I'm interested in reinforcement learning, robotics, unsupervised learning, and meta learning. Also check out my Google Scholar page.

I co-organized the NIPS 2017 Deep RL Symposium and the first Deep RL Bootcamp (now Full Stack Deep Learning Bootcamp).

I served as GSI of the very first offering of the Deep RL Course at UC Berkeley (now a regular offering).

You can reach me at rocky@covariant.ai.