Alex X. Lee



alexleegk [at] gmail [dot] com



I am currently a Research Scientist at DeepMind.

I am interested in methods that can enable robots to acquire complex sensorimotor skills in the real world. This involves methods that can reason with raw sensor measurements and efficiently learn from real-world data, including model-based and model-free reinforcement learning, representation learning, transfer learning, and learning from demonstrations.

I completed my Ph.D. in Computer Science at UC Berkeley and my B.S. in Electrical Engineering and Computer Science at this same university. My Ph.D. work focused on learning visual dynamics models for robots and using these models for control and planning. Previously, I have also worked on motion planning, learning from demonstations, and visual tracking.

In my free time, I enjoy working on electronics and DIY projects, flying RC aircrafts, and visiting new places with friends.