A3C 算法
A3C (Asynchronous Advantage Actor-Critic) 是结合了 Policy Based 和 Value Based 的算法。
Press ← or → to navigate between chapters
Press S or / to search in the book
Press ? to show this help
Press Esc to hide this help
A3C (Asynchronous Advantage Actor-Critic) 是结合了 Policy Based 和 Value Based 的算法。