Co-founder; professor at UC Berkeley at Physical Intelligence · Professor, EECS at Gorilla
Sergey Levine
Sergey Levine is a professor in EECS at UC Berkeley, which they joined in 2016, and a co-founder of Physical Intelligence.
About
Their research covers reinforcement learning, imitation learning and scalable robot learning. Levine's group developed guided policy search and end-to-end visuomotor policy training, and contributed to offline RL methods such as CQL and IQL.
Known for
- 01
Professor at UC Berkeley, RAIL lab
- 02
Guided policy search and visuomotor policies
- 03
Offline RL methods CQL, AWAC and IQL
Activity
Works per year
14.7k citations
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor2018
13.5k citations
7.2k citations
5.8k citations
Public data only, fetched 2026-11-17. GitHub counts cover public contributions; Hugging Face counts are repositories created; research data comes from OpenAlex.
Labs
Sources
Compiled from public sources. Something wrong, or would you like this page changed or removed? Tell us on Discord or open an issue on GitHub and we will act promptly.

