Sergey Levine on Robot Learning & Offline RL
An interview with professor Sergey Levine, who researches Deep Reinforcement Learning with an emphasis on robotics, Offline Reinforcement Learning, and much more
In episode 11 of The Gradient Podcast, we interview Sergey Levine, a professor at Berkeley whose research focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms for robotics.
Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms, and includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.
Podcast Theme: “MusicVAE: Trio 16-bar Sample #2” from "MusicVAE: A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music".