add saved model of pong and breakout, update README.MD

fluid/DeepQNetwork/README.md

-# Reproduce DQN, DoubleDQN, DuelingDQN model with fluid version of PaddlePaddle
+# 基于PaddlePaddle的Fluid版本复现DQN, DoubleDQN, DuelingDQN三个模型
 
-+ DQN in:
++ DQN模型： 
 [Human-level Control Through Deep Reinforcement Learning](http://www.nature.com/nature/journal/v518/n7540/full/nature14236.html)
-+ DoubleDQN in:
++ DoubleDQN模型：
 [Deep Reinforcement Learning with Double Q-Learning](https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/viewPaper/12389)
-+ DuelingDQN in:
++ DuelingDQN模型：
 [Dueling Network Architectures for Deep Reinforcement Learning](http://proceedings.mlr.press/v48/wangf16.html)
 
-# Atari benchmark & performance
-## [Atari games introduction](https://gym.openai.com/envs/#atari)
+# Atari游戏表现
+## [Atari游戏介绍](https://gym.openai.com/envs/#atari)
 
-+ Pong game result
++ Pong游戏训练结果
 ![DQN result](assets/dqn.png)
 
-# How to use
-+ Dependencies:
+# 使用教程
++ 依赖:
     + python2.7
     + gym
     + tqdm
+    + opencv-python
     + paddlepaddle-gpu==0.12.0
 
-+ Start Training:
+    可以通过以下命令来下载所需依赖：
     ```
-    # To train a model for Pong game with gpu (use DQN model as default)
+    pip install -r requirement.txt 
+    ```
+
++ 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
 
-    # To train a model for Pong with DoubleDQN
+    # 训练DoubleDQN模型
     python train.py --rom ./rom_files/pong.bin --use_cuda --alg DoubleDQN
 
-    # To train a model for Pong with DuelingDQN
+    # 训练DuelingDQN模型
     python train.py --rom ./rom_files/pong.bin --use_cuda --alg DuelingDQN
     ```
 
-To train more games, can install more rom files from [here](https://github.com/openai/atari-py/tree/master/atari_py/atari_roms)
+    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)
 
-+ Start Testing:
++ 测试模型： 
     ```
     # Play the game with saved model and calculate the average rewards
-    python play.py --rom ./rom_files/pong.bin --use_cuda --model_path ./saved_model/DQN-pong/stepXXXXX
+    # 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
 
-    # Play the game with visualization
-    python play.py --rom ./rom_files/pong.bin --use_cuda --model_path ./saved_model/DQN-pong/stepXXXXX --viz 0.01
+    # 以可视化的形式来玩游戏
+    python play.py --rom ./rom_files/pong.bin --use_cuda --model_path ./saved_model/DQN-pong --viz 0.01
     ```

fluid/DeepQNetwork/play.py

@@ -11,7 +11,7 @@ from tqdm import tqdm
 
 def predict_action(exe, state, predict_program, feed_names, fetch_targets,
                    action_dim):
-    if np.random.randint(100) == 0:
+    if np.random.random() < 0.001:
         act = np.random.randint(action_dim)
     else:
         state = np.expand_dims(state, axis=0)

fluid/DeepQNetwork/train.py

@@ -120,6 +120,9 @@ def train_agent():
     pbar = tqdm(total=1e8)
     recent_100_reward = []
     total_step = 0
+    max_reward = None
+    save_path = os.path.join(args.model_dirname, '{}-{}'.format(
+                args.alg, os.path.basename(args.rom).split('.')[0]))
     while True:
         # start epoch
         total_reward, step = run_train_episode(agent, env, exp)
@@ -134,11 +137,8 @@ def train_agent():
             print("eval_agent done, (steps, eval_reward): ({}, {})".format(
                 total_step, eval_reward))
             
-        if total_step // args.save_every_steps == save_flag:
-            save_flag += 1
-            save_path = os.path.join(args.model_dirname, '{}-{}'.format(
-                args.alg, os.path.basename(args.rom).split('.')[0]),
-                                     'step{}'.format(total_step))
+            if max_reward is None or eval_reward > max_reward:
+                max_reward = eval_reward
                 fluid.io.save_inference_model(save_path, ['state'],
                                               agent.pred_value, agent.exe,
                                               agent.predict_program)
@@ -173,11 +173,6 @@ if __name__ == '__main__':
         type=str,
         default='saved_model',
         help='dirname to save model')
-    parser.add_argument(
-        '--save_every_steps',
-        type=int,
-        default=100000,
-        help='every steps number to save model')
     parser.add_argument(
         '--test_every_steps',
         type=int,