update

codes/common/model.py

@@ -5,7 +5,7 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2021-03-12 21:14:12
 LastEditor: John
-LastEditTime: 2021-03-31 13:49:06
+LastEditTime: 2021-05-04 02:45:27
 Discription: 
 Environment: 
 '''
@@ -63,7 +63,7 @@ class Actor(nn.Module):
     def forward(self, x):
         x = F.relu(self.linear1(x))
         x = F.relu(self.linear2(x))
-        x = F.tanh(self.linear3(x))
+        x = torch.tanh(self.linear3(x))
         return x
 
 class ActorCritic(nn.Module):

codes/common/utils.py

@@ -5,7 +5,7 @@ Author: John
 Email: johnjim0816@gmail.com
 Date: 2021-03-12 16:02:24
 LastEditor: John
-LastEditTime: 2021-04-29 15:32:38
+LastEditTime: 2021-05-04 19:58:31
 Discription: 
 Environment: 
 '''
@@ -13,10 +13,8 @@ import os
 import numpy as np
 from pathlib import Path
 
-
-
 def save_results(rewards,ma_rewards,tag='train',path='./results'):
-    '''保存reward等结果
+    '''save rewards and ma_rewards
     '''
     np.save(path+'{}_rewards.npy'.format(tag), rewards)
     np.save(path+'{}_ma_rewards.npy'.format(tag), ma_rewards)