2
$\begingroup$

I'm trying to find out what kind of policy improvement and policy evaluation AlphaGo, AlphaGo Zero, and AlphaZero are using. By looking into their respective paper and SI, I can conclude that it is a kind of policy gradient actor-critic approach, where the policy is evaluated by a critic and is improved by and actor. Yet still can't fit it to any of the known policy gradient algorithms.

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.