Skip to content
ml-recall

#ddpg

1 question from PyTorch

Timed test

1 question · 1 min · score and explanations at the end

Take a test
Q 1 / 1Score 0 / 0

Question 1: Short answer

hardAI-checkedPyTorch

In a DDPG implementation the critic forgets to squeeze its output:

r, d = batch["rew"], batch["done"]       # both shape (100,)
q_pi_targ = q_targ(o2, pi_targ(o2))      # shape (100, 1) -- not squeezed
backup = r + gamma * (1 - d) * q_pi_targ

What is the shape of backup?

Two dimensions, e.g. (8, 4)