Dive into a 25-minute tutorial that breaks down the mathematical foundations of reinforcement learning in neural networks step by step. Learn how derivatives are calculated (BAM!), updated with rewards (DOUBLE BAM!!), and utilized to optimize neural network parameters (TRIPLE BAM!!!). Follow along as the instructor methodically explains each concept, starting with an introduction, moving through derivative calculations, showing how to update derivatives using rewards, demonstrating parameter updates in neural networks, and concluding with an additional example for reinforcement. Perfect for those wanting to understand the mathematical details behind reinforcement learning implementations.

Syllabus

0:00 Awesome song and introduction
4:09 Calculating a derivative
12:16 Updating the derivative with a reward
15:39 Updating a parameter in the neural network
16:28 A second example