Dive into the training loop of Deep Q-Networks (DQN) in this 21-minute tutorial video, part 4 of a series on Q Learning. Explore the implementation details, including the policy, for loop, and reward mechanisms. Access the accompanying code on GitHub and refer to the original DQN paper for a deeper understanding. Ensure familiarity with previous videos in the series for a comprehensive grasp of Q Learning concepts.
Overview
Syllabus
Introduction
Training Leap
Policy
For Loop
Ord Reward
Append Reward
Taught by
Edan Meyer