0
$\begingroup$

Which policy gradient method is used that deals with continuous action spaces?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
0
$\begingroup$

You can use Soft Actor Critic or PPO from the same website. Most PG methods can be used in discrete and/or continuous action spaces.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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