Skip to main content

Reinforcement Learning with Neural Networks: Mathematical Details

statquestApril 14, 202525:01ai_ml_education

Summary

This video delves into the mathematical details of updating neural network parameters using reinforcement learning, covering derivative calculations and optimization processes. It is highly useful for students and educators who are learning fundamental AI/ML concepts and wish to understand the underlying mechanics of reinforcement learning algorithms.

Description

Here we go through the math required to update a parameter in a neural network using reinforcement learning and we do it one step a time. We show how the derivatives are calculated (BAM!), then updated (DOUBLE BAM!!), and then used to optimize the parameters (TRIPLE BAM!!!). If you'd like to support StatQuest, please consider... Patreon: https://www.patreon.com/statquest ...or... YouTube Membership: https://www.youtube.com/channel/UCtYLUTtgS3k1Fg4y5tAhLbw/join ...buying a book, a study guide, a t-shirt or hoodie, or a song from the StatQuest store... https://statquest.org/statquest-store/ ...or just donating to StatQuest! paypal: https://www.paypal.me/statquest venmo: @JoshStarmer Lastly, if you want to keep up with me as I research and create new StatQuests, follow me on twitter: https://twitter.com/joshuastarmer 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 #StatQuest