This series on artificial intelligence explores recent breakthroughs of AI, its broader societal implications and its future potential. In this presentation, Sergey Levine, associate professor of Electrical Engineering and Computer Science at UC Berkeley, discusses AI reinforcement learning methods. Levine asks what it would take to create machine learning systems that can make decisions when faced with the full complexity and diversity of the real world, while still retaining the ability of reinforcement learning to come up with new solutions? He discusses how advances in offline reinforcement learning can enable machine learning systems to learn 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. 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. 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. Series: "The Future of AI" [Science] [Show ID: 38857]