An introduction to deep reinforcement learning | DKU Colloquium | Keith Ross
Much of the excitement in AI is due to recent advances in Deep Reinforcement Learning (DRL). By using DRL to overcome the curse of dimensionality in dynamic programming, researchers have recently made surprising breakthroughs in learning to play Go and the Atari video games, and learning to control high-dimensional robotic locomotion. In this talk, we will review some of the major developments in DRL since 2015, including AlphaZero, Deep Q-Learning, and actor-critic algorithms. We will also briefly describe some of our own recent work in the area.
Keith Ross is dean of engineering and computer science at NYU Shanghai and co-director of the university’s Center of Data Science and Artificial Intelligence. Previously, he was a full professor at the University of Pennsylvania, Eurecom Institute, Polytechnic Institute, and NYU. He has a Ph.D. in computer and control engineering from the University of Michigan. He has received several prestigious best paper awards, and his work has featured in the mainstream press. He is co-author of the most popular textbook on computer networking, which has been translated into 13 languages. He is also an ACM Fellow and an IEEE Fellow. His current research interests are in reinforcement learning. He has also worked in internet privacy, peer-to-peer networking, internet measurement, stochastic modeling of computer networks, queuing theory, and Markov decision processes. At NYU Shanghai, he has been teaching machine learning, reinforcement learning, and computer programming.
Co-hosted by DKU Colloquium and Data Science Research Center, this colloquium is open to DKU community members only. Contact email: email@example.com