bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update ch5

Browse Source
This commit is contained in:
qiwang
2025-02-09 12:54:49 +08:00
parent c458b7fd3e
commit 54ab1e8bfa
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/chapter5/chapter5.md
View File

@@ -207,7 +207,7 @@ $$
图 5.2 的横轴代表 $\frac{p_{\theta}\left(a_{t} | s_{t}\right)}{p_{\theta^{k}}\left(a_{t} | s_{t}\right)}$，纵轴代表裁剪函数的输出。
* 如果 $\frac{p_{\theta}\left(a_{t} | s_{t}\right)}{p_{\theta^{k}}\left(a_{t} | s_{t}\right)}$ 大于$1+\varepsilon$，输出就是 $1+\varepsilon$；
* 如果小于 $1-\varepsilon$，输出就是 $1-\varepsilon$；
* 如果介于 $1+\varepsilon$ \~{} $1-\varepsilon$，输出等于输入。
* 如果介于 $1-\varepsilon \sim 1+\varepsilon$，输出等于输入。
<div align=center>
<img width="550" src="../img/ch5/5.2.png"/>
@@ -249,4 +249,3 @@ $$