From d4183b75ce7e7f06ad41c6aefd71079459b7e251 Mon Sep 17 00:00:00 2001
From: Yiyuan Yang <yyy1997sjz@gmail.com>
Date: Tue, 25 May 2021 13:56:12 +0800
Subject: [PATCH] Update chapter5.md

---
 docs/chapter5/chapter5.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/chapter5/chapter5.md b/docs/chapter5/chapter5.md
index 4202e03..8a9bc91 100644
--- a/docs/chapter5/chapter5.md
+++ b/docs/chapter5/chapter5.md
@@ -157,7 +157,7 @@ PPO 有一个前身叫做`信任区域策略优化(Trust Region Policy Optimizat
 $$
 \begin{aligned}
 J_{T R P O}^{\theta^{\prime}}(\theta)=E_{\left(s_{t}, a_{t}\right) \sim \pi_{\theta^{\prime}}}\left[\frac{p_{\theta}\left(a_{t} | s_{t}\right)}{p_{\theta^{\prime}}\left(a_{t} | s_{t}\right)} A^{\theta^{\prime}}\left(s_{t}, a_{t}\right)\right] \\ \\
-<p align="right"> \mathrm{KL}\left(\theta, \theta^{\prime}\right)<\delta </p>
+ \mathrm{KL}\left(\theta, \theta^{\prime}\right)<\delta 
 \end{aligned}
 $$