Video
Description
Please note: since last teaching the Policy Gradient content we have discovered two logical errors. Will be updating & reposting the content soon. Stay tuned.
In previous lectures, you were introduced to DQN - an algorithm that falls under the first major branch of Reinforcement Learning, “Value Based Methods”. In this lecture, we introduce you to “Policy Gradient methods” the second major branch of Reinforcement Learning where we learn to manipulate the object we care about the most - the policy - directly.
Lecture Slides
…
Exercise
Follow the link below to access the exercises for lecture 7:
Exercise Solutions
Follow the link below to access the exercise solutions for lecture 7:
Additional Learning Material
…