diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/models/sarsa_model.pkl b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/models/sarsa_model.pkl
deleted file mode 100644
index ff25fd5..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/models/sarsa_model.pkl and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_ma_rewards.npy b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_ma_rewards.npy
deleted file mode 100644
index d7d62e3..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_ma_rewards.npy and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards.npy b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards.npy
deleted file mode 100644
index de0a816..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards.npy and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards_curve.png b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards_curve.png
deleted file mode 100644
index 3de2db7..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/eval_rewards_curve.png and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_ma_rewards.npy b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_ma_rewards.npy
deleted file mode 100644
index 3f9bf83..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_ma_rewards.npy and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards.npy b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards.npy
deleted file mode 100644
index e0fd7e9..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards.npy and /dev/null differ
diff --git a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards_curve.png b/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards_curve.png
deleted file mode 100644
index 0a8cd37..0000000
Binary files a/codes/Sarsa/outputs/CliffWalking-v0/20210506-171245/results/train_rewards_curve.png and /dev/null differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/models/sarsa_model.pkl b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/models/sarsa_model.pkl
new file mode 100644
index 0000000..a80fa68
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/models/sarsa_model.pkl differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_ma_rewards.npy b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_ma_rewards.npy
new file mode 100644
index 0000000..91051de
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_ma_rewards.npy differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards.npy b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards.npy
new file mode 100644
index 0000000..176ea2e
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards.npy differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards_curve.png b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards_curve.png
new file mode 100644
index 0000000..a72aede
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/eval_rewards_curve.png differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_ma_rewards.npy b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_ma_rewards.npy
new file mode 100644
index 0000000..47c20c6
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_ma_rewards.npy differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards.npy b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards.npy
new file mode 100644
index 0000000..204a158
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards.npy differ
diff --git a/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards_curve.png b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards_curve.png
new file mode 100644
index 0000000..22e9755
Binary files /dev/null and b/codes/Sarsa/outputs/RacetrackEnv/20210715-085005/results/train_rewards_curve.png differ
diff --git a/codes/Sarsa/task0_train.py b/codes/Sarsa/task0_train.py
index 7fad1ab..c8363bc 100644
--- a/codes/Sarsa/task0_train.py
+++ b/codes/Sarsa/task0_train.py
@@ -5,7 +5,7 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2021-03-11 17:59:16
 LastEditor: John
-LastEditTime: 2021-07-14 17:27:40
+LastEditTime: 2021-07-15 08:49:31
 Discription: 
 Environment: 
 '''
@@ -52,14 +52,16 @@ def train(cfg,env,agent):
         # An episode is an array of (state, action, reward) tuples
         state = env.reset()
         ep_reward = 0
+        action = agent.choose_action(state)
         while True:
         # for t in range(cfg.n_steps):
-            action = agent.choose_action(state)
+            
             next_state, reward, done = env.step(action)
             ep_reward+=reward
             next_action = agent.choose_action(next_state)
             agent.update(state, action, reward, next_state, next_action,done)
             state = next_state
+            action = next_action
             if done:
                 break  
         if ma_rewards: