nothing

PPO.py

@@ -241,7 +241,7 @@ class Arguments:
         self.num_threads = 32  # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
 
         '''Arguments for training'''
-        self.num_episode = 2000  # to control the train episodes for PPO
+        self.num_episode = 1000  # to control the train episodes for PPO
         self.gamma = 0.995  # discount factor of future rewards
         self.learning_rate = 2 ** -14  # 2e-4
         self.soft_update_tau = 2 ** -8  # 2 ** -8 ~= 5e-3

module.py

@@ -126,7 +126,6 @@ class Wind:
                                   self.power_coefficient * self.generator_efficiency) / 1e3
         else:
             self.current_power = 0
-
         return self.current_power
 
     def gen_cost(self, current_power):

tools.py

@@ -129,7 +129,7 @@ class Arguments:
         self.num_threads = 32  # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
 
         '''Arguments for training'''
-        self.num_episode = 2000
+        self.num_episode = 1000
         self.gamma = 0.995  # discount factor of future rewards
         # self.reward_scale = 1  # an approximate target reward usually be closed to 256
         self.learning_rate = 2 ** -14  # 2 ** -14 ~= 6e-5