Skip to content

Commit

Permalink
update
Browse files Browse the repository at this point in the history
  • Loading branch information
johnjim0816 committed Jul 29, 2023
1 parent a4c2a3e commit ab5b369
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion docs/ch9/main.md
Original file line number Diff line number Diff line change
Expand Up @@ -252,4 +252,4 @@ $$
\nabla_\theta \log \pi_\theta(s, a)==\frac{\left(a-\phi(s)^T \theta\right) \phi(s)}{\sigma^2}
$$

这个公式虽然看起来很复杂,但实现起来其实很简单,只需要在模型最后一层输出两个值,一个是均值,一个是方差,然后再用这两个值来构建一个高斯分布,然后采样即可。
这个公式虽然看起来很复杂,但实现起来其实很简单,只需要在模型最后一层输出两个值,一个是均值,一个是方差,然后再用这两个值来构建一个高斯分布,然后采样即可,具体同样在实战中展开

0 comments on commit ab5b369

Please sign in to comment.