Sergey Levine
UC Berkeley professor of robot learning and deep reinforcement learning; co-founder of Physical Intelligence.
At a glance
Also on this page: Key facts · Links · Sources · Related pages
- Sergey Levine is a computer scientist at UC Berkeley, where he joined the Department of Electrical Engineering and Computer Sciences in fall 2016 and leads the Robotic Artificial Intelligence and Learning Lab.
- His work is on learning for decision making and control: deep and offline reinforcement learning, guided policy search and end-to-end visuomotor policies for robots.
- He co-founded the robotics company Physical Intelligence.
- His Berkeley page calls him an associate professor; Wikipedia calls him a professor.
Key facts
- Current role
- Associate professor, Department of Electrical Engineering and Computer Sciences, UC Berkeley, from fall 2016 (his Berkeley page); leads the Robotic Artificial Intelligence and Learning Lab (RAIL)2
- Company
- Co-founder of Physical Intelligence1
- Education
- BS and MS in computer science, Stanford University (2009); PhD in computer science, Stanford (2014)2
- Earlier
- Postdoctoral researcher with Pieter Abbeel at Berkeley's Robot Learning Lab; part-time research scientist at Google from 2015; faculty at the University of Washington before Berkeley1
- Research
- Guided policy search, end-to-end visuomotor policy learning, model-based and offline reinforcement learning from large robot datasets1
- Awards
- MIT Technology Review Innovators Under 35 (2016); Presidential Early Career Award for Scientists and Engineers (2025)1
Roles
Connections
Links
Sources
Last checked against its sources today
Is something on this page wrong or out of date? Tell us
How recent
The line under a date fills as time passes: empty when new, then one equal share each for a day, a week, a month and a year. For episodes and other items it is full at 2 years; for "last checked", at a year. A striped line means the date is known only to the month or year.