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.


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.