From 2448dd5e4c42f21dd47b7ada085411fadbb3cfda Mon Sep 17 00:00:00 2001
From: zenghsh3 <zenghongsheng@baidu.com>
Date: Tue, 26 Jun 2018 11:09:13 +0800
Subject: [PATCH] Fix with pre-commit

---
 fluid/DeepQNetwork/README.md    |  2 +-
 fluid/DeepQNetwork/README_cn.md | 12 ++++++------
 fluid/DeepQNetwork/train.py     |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fluid/DeepQNetwork/README.md b/fluid/DeepQNetwork/README.md
index 83ce1368..2a2db7cb 100644
--- a/fluid/DeepQNetwork/README.md
+++ b/fluid/DeepQNetwork/README.md
@@ -29,7 +29,7 @@ Based on PaddlePaddle's next-generation API Fluid, the DQN model of deep reinfor
         recommended to compile and install PaddlePaddle from source code
     + Install other dependencies:
         ```
-        pip install -r requirement.txt 
+        pip install -r requirement.txt
         pip install gym[atari]
         ```
         Install ale_python_interface, can reference：https://github.com/mgbellemare/Arcade-Learning-Environment
diff --git a/fluid/DeepQNetwork/README_cn.md b/fluid/DeepQNetwork/README_cn.md
index 130144fa..87eb6123 100644
--- a/fluid/DeepQNetwork/README_cn.md
+++ b/fluid/DeepQNetwork/README_cn.md
@@ -1,6 +1,6 @@
 # 基于PaddlePaddle的Fluid版本复现DQN, DoubleDQN, DuelingDQN三个模型
 基于PaddlePaddle下一代API Fluid复现了深度强化学习领域的DQN模型，在经典的Atari 游戏上复现了论文同等水平的指标，模型接收游戏的图像作为输入，采用端到端的模型直接预测下一步要执行的控制信号，本仓库一共包含以下3类模型。
-+ DQN模型： 
++ DQN模型：
 [Human-level Control Through Deep Reinforcement Learning](http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html)
 + DoubleDQN模型：
 [Deep Reinforcement Learning with Double Q-Learning](https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/viewPaper/12389)
@@ -19,15 +19,15 @@
     + gym
     + tqdm
     + opencv-python
-    + paddlepaddle-gpu>=0.12.0 
+    + paddlepaddle-gpu>=0.12.0
     + ale_python_interface
 
 + 下载依赖：
     + 安装PaddlePaddle：
-        建议通过PaddlePaddle源码进行编译安装    
+        建议通过PaddlePaddle源码进行编译安装  
     + 下载其它依赖：
         ```
-        pip install -r requirement.txt 
+        pip install -r requirement.txt
         pip install gym[atari]
         ```
         安装ale_python_interface可以参考：https://github.com/mgbellemare/Arcade-Learning-Environment
@@ -46,10 +46,10 @@
 
     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） 
+    # 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）
     python play.py --rom ./rom_files/pong.bin --use_cuda --model_path ./saved_model/DQN-pong
 
     # 以可视化的形式来玩游戏
diff --git a/fluid/DeepQNetwork/train.py b/fluid/DeepQNetwork/train.py
index ffbe099c..63439be7 100644
--- a/fluid/DeepQNetwork/train.py
+++ b/fluid/DeepQNetwork/train.py
@@ -122,7 +122,7 @@ def train_agent():
     total_step = 0
     max_reward = None
     save_path = os.path.join(args.model_dirname, '{}-{}'.format(
-                args.alg, os.path.basename(args.rom).split('.')[0]))
+        args.alg, os.path.basename(args.rom).split('.')[0]))
     while True:
         # start epoch
         total_reward, step = run_train_episode(agent, env, exp)
@@ -136,7 +136,7 @@ def train_agent():
             test_flag += 1
             print("eval_agent done, (steps, eval_reward): ({}, {})".format(
                 total_step, eval_reward))
-            
+
             if max_reward is None or eval_reward > max_reward:
                 max_reward = eval_reward
                 fluid.io.save_inference_model(save_path, ['state'],
-- 
GitLab