Sergey Levine
UC Berkeley associate professor working on robot learning; co-author of the π0 robot foundation model paper
- Associate Professor, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley15
Sergey Levine is an Associate Professor in the Department of Electrical Engineering and Computer Sciences at UC Berkeley, where Levine's research group, the Robotic Artificial Intelligence and Learning Lab (RAIL), works on algorithms that let autonomous agents and robots learn complex behaviors. Levine is a co-author of the π0 vision-language-action flow model paper, and the π0 model is published in Physical Intelligence's open-source openpi repository. Levine also co-authored the Trust Region Policy Optimization paper and teaches CS 185/285 Deep Reinforcement Learning at Berkeley, with lecture recordings shared publicly.12345
Work
π0 (openpi)Open-source code
Co-author of "π0: A Vision-Language-Action Flow Model for General Robot Control" (2024). The Apache-2.0 openpi repository, published by the Physical Intelligence team, provides the π0 model with base checkpoints for fine-tuning.23
CS 185/285 Deep Reinforcement Learning (external site: rail.eecs.berkeley.edu)Published research
Listed as the instructor of the UC Berkeley deep reinforcement learning course, whose site links lecture recordings and materials from previous offerings.5
Trust Region Policy Optimization (TRPO) (external site: arxiv.org)Published research
Co-author with John Schulman, Philipp Moritz, Michael I. Jordan and Pieter Abbeel of the 2015 paper describing the TRPO policy optimization algorithm.4
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.