A3C vs PPO
#15
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
{{ message }}
-
What is the essential part (both code and in paper) that transform Penseive-A3C to Penseive-PPO?
To my understanding, the adaptive entropy weight in Suphx: Mastering Mahjong with Deep Reinforcement Learning∗ , and clipping the policy. These two points are the update to the value function of A3C.
Am I right?
Could you please elaborate with reference to paper and page, and code and line?
Beta Was this translation helpful? Give feedback.
All reactions