Sergey LevineAn Ecological Perspective on Reinforcement LearningIt has nothing to do with rainforests, at least not necessarily. J. J. Gibson’s seminal work “The Ecological Approach to Visual Perception”…12 min read·Dec 15, 2021--2--2
Sergey LevineUnderstanding the World Through Action: RL as a Foundation for Scalable Self-Supervised LearningMachine learning systems have mastered a breadth of challenging problems in domains ranging from computer vision to speech recognition and…11 min read·Oct 26, 2021--2--2
Sergey LevineHow Robots Can Learn End-to-End From DataThe year is 2030, and you’ve purchased a brand-new general-purpose home robot. The robot comes equipped with a few skills that it knows how…15 min read·Apr 29, 2021--2--2
Sergey LevineDecisions from Data: How Offline Reinforcement Learning Will Change How We Use MLOffline RL will change how we make decisions with data. How do offline RL methods work, and what are some open challenges in this field?13 min read·Sep 15, 2020--3--3