提交 882abf27 编写于 作者: X xiaowei_xing

test

上级 521890f8
......@@ -337,4 +337,12 @@ $$
$$
= \phi(s,a) - \sum_{a'} \phi(s,a') \frac{e^{\phi(s,a')^{\text{T}}\theta}}{\sum_{a''}e^{\phi(s,a'')^{\text{T}}\theta}}
$$
$$
= \phi(s,a) - \sum_{a'} \phi(s,a') \pi_{\theta}(a'|s)
$$
$$
= \phi(s,a) - \mathbb{E}_ {a'\sim\pi_{\theta}(a'|s)}[\phi(s,a')]
$$
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册