275: Machine Learning Through Reinforcement & Contextual Bandits

In this episode of the SuperDataScience Podcast, I chat with the Machine Learning Research Scientist, John Langford. You will hear about unsupervised, supervised learning and reinforcement learning, and the differences between the three. You will learn about applications of contextual bandits and reinforcement learning in general, YOLO style algorithms versus simulator algorithms, technics for avoiding local optimums. You will also learn about the balance between exploration and exploitation, learning to search and active learning. If you enjoyed this episode, check out show notes, resources, and more at www.superdatascience.com/275