diff --git a/fluid/DeepQNetwork/README.md b/fluid/DeepQNetwork/README.md
index 2a2db7cb76c26227d640cfc4f5972771f8c53ac0..46cdb899102281f92e13ce261e1db82e38f935d5 100644
--- a/fluid/DeepQNetwork/README.md
+++ b/fluid/DeepQNetwork/README.md
@@ -16,7 +16,7 @@ Based on PaddlePaddle's next-generation API Fluid, the DQN model of deep reinfor
 ![DQN result](assets/dqn.png)
 
 # How to use
-+ Dependencies:
+### Dependencies:
     + python2.7
     + gym
     + tqdm
@@ -24,7 +24,7 @@ Based on PaddlePaddle's next-generation API Fluid, the DQN model of deep reinfor
     + paddlepaddle-gpu>=0.12.0
     + ale_python_interface
 
-+ Install Dependencies:
+### Install Dependencies:
     + Install PaddlePaddle:
         recommended to compile and install PaddlePaddle from source code
     + Install other dependencies:
@@ -35,7 +35,7 @@ Based on PaddlePaddle's next-generation API Fluid, the DQN model of deep reinfor
         Install ale_python_interface, can reference：https://github.com/mgbellemare/Arcade-Learning-Environment
 
 
-+ Start Training:
+### Start Training:
     ```
     # To train a model for Pong game with gpu (use DQN model as default)
     python train.py --rom ./rom_files/pong.bin --use_cuda
@@ -49,7 +49,7 @@ Based on PaddlePaddle's next-generation API Fluid, the DQN model of deep reinfor
 
     To train more games, can install more rom files from [here](https://github.com/openai/atari-py/tree/master/atari_py/atari_roms)
 
-+ Start Testing:
+### Start Testing:
     ```
     # Play the game with saved best model and calculate the average rewards
     python play.py --rom ./rom_files/pong.bin --use_cuda --model_path ./saved_model/DQN-pong
diff --git a/fluid/DeepQNetwork/README_cn.md b/fluid/DeepQNetwork/README_cn.md
index 87eb61238aa6b81d83b23cb6ea3a18bccff9618e..c1573fe9d75d9aaef578ce95518b0e03191c892b 100644
--- a/fluid/DeepQNetwork/README_cn.md
+++ b/fluid/DeepQNetwork/README_cn.md
@@ -14,7 +14,7 @@
 ![DQN result](assets/dqn.png)
 
 # 使用教程
-+ 依赖:
+### 依赖:
     + python2.7
     + gym
     + tqdm
@@ -22,7 +22,7 @@
     + paddlepaddle-gpu>=0.12.0
     + ale_python_interface
 
-+ 下载依赖：
+### 下载依赖：
     + 安装PaddlePaddle：
         建议通过PaddlePaddle源码进行编译安装  
     + 下载其它依赖：
@@ -32,7 +32,7 @@
         ```
         安装ale_python_interface可以参考：https://github.com/mgbellemare/Arcade-Learning-Environment
 
-+ 训练模型：
+### 训练模型：
     ```
     # 使用GPU训练Pong游戏（默认使用DQN模型）
     python train.py --rom ./rom_files/pong.bin --use_cuda
@@ -46,7 +46,7 @@
 
     训练更多游戏，可以下载游戏rom从[这里](https://github.com/openai/atari-py/tree/master/atari_py/atari_roms)
 
-+ 测试模型：
+### 测试模型：
     ```
     # Play the game with saved model and calculate the average rewards
     # 使用训练过程中保存的最好模型玩游戏，以及计算平均奖励（rewards）