Loading Events
  • This event has passed.

CITRIS Research Exchange and BAIR Present: Sergey Levine on Reinforcement Learning in AI

Banner with blue circles and circuit shapes on white background. Four photos of speakers with dates on them and names under. Text reads: CITRIS Research Exchange and BAIR present Four Distinguished Lectures on the Status and Future of AI. Speakers are: Stuart Russell, April 5th. Sergey Levine, April 12th. Michael I Jordan, April 19th. Pamela Samuelson, April 26th.

Talk Title: “Reinforcement Learning With Large Datasets: a Path to Resourceful Autonomous Agents”

Speaker: Sergey Levine, Associate Professor of Electrical Engineering and Computer Science, UC Berkeley

Register To Attend | Watch Livestream on YouTube

Abstract: One of the most remarkable things about recent generative machine learning systems is their ability to produce generations that seem like something humans would create. In contrast, one of the most remarkable things about reinforcement learning methods, such as AlphaGo, is precisely that they can come up with solutions, such as Move 37, that solve problems in unexpected ways. But such methods are difficult to apply to settings that, unlike the game of Go, are not constrained by simple rules. What would it take to create machine learning systems that can make decisions when faced with the full complexity of the real world, while retaining the ability to come up with new solutions? In this talk, Levine will discuss how advances in offline reinforcement learning can enable machine learning systems to make more optimal decisions from data, combining the best of data-driven machine learning with the capacity for emergent behavior and optimization provided by reinforcement learning.

Sergey Levine. Speaker Bio: Sergey Levine received a B.S. and M.S. 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. Applications of his work include autonomous robots and vehicles, as well as applications in other decision-making domains. His research 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.

About the Talk: Co-hosted with the UC Berkeley Artificial Intelligence Research Group (BAIR)

About the Series: CITRIS Research Exchange delivers fresh perspectives on information technology and society from distinguished academic, industry and civic leaders. Free and open to the public, these seminars feature leading voices on societal-scale research issues. Presentations take place on Wednesdays from noon to 1 p.m. PT. Have an idea for a great talk? Please feel free to suggest potential speakers for our series.

Sign up to receive the latest news and updates from CITRIS.