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 Answer 1

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
    Commented Mar 22, 2020 at 10:38

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .