Question: When we attempt to use Stochastic Gradient Descent ( SGD ) to learn value functions and use a bootstrapped target ( using TD learning )
When we attempt to use Stochastic Gradient Descent SGD to learn value functions and use a bootstrapped target using TD learning the technique used is referred to in the book as a semigradient method.
Which of the following properties of semigradient techniques hold?
Step by Step Solution
There are 3 Steps involved in it
1 Expert Approved Answer
Step: 1 Unlock
Question Has Been Solved by an Expert!
Get step-by-step solutions from verified subject matter experts
Step: 2 Unlock
Step: 3 Unlock
