2
$\begingroup$

Why is the actor-critic algorithm limited to using on-policy data? Or can we use the actor-critic algorithm with off-policy data?

$\endgroup$
1
$\begingroup$

It's because, in the actor-critic algorithm, the objective function is an expectation under the $\tau$ of the policy. If we want to use off-policy data, we have to resort to importance sampling relative to the other policy.

$\endgroup$
1
  • $\begingroup$ What does the tau value mean? $\endgroup$
    – asaf92
    Mar 22 '20 at 10:38

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.