I Read Andrew Ng's PhD Thesis

Jordan, a PhD student at MIT, reviews Andrew Ng's thesis on reinforcement learning. The video explores Ng's contributions to AI, including his work on Google Brain and Coursera. It delves into reinforcement learning concepts, Markov Decision Processes, shaping techniques, and the Pegasus method. The video also discusses the application of these concepts to autonomous helicopters. Jordan reflects on the accessibility of Ng's work and invites viewers to suggest other theses for review.

What new insight or understanding did you gain from this video?