update

codes/common/memory.py

@@ -5,30 +5,28 @@
 @Email: johnjim0816@gmail.com
 @Date: 2020-06-10 15:27:16
 @LastEditor: John
-LastEditTime: 2021-03-13 11:37:15
+LastEditTime: 2021-09-15 02:17:59
 @Discription: 
 @Environment: python 3.7.7
 '''
 import random
-
 class ReplayBuffer:
-    
     def __init__(self, capacity):
-        self.capacity = capacity
-        self.buffer = []
-        self.position = 0
+        self.capacity = capacity # 经验回放的容量
+        self.buffer = [] # 缓冲区
+        self.position = 0 
     
     def push(self, state, action, reward, next_state, done):
+        ''' 缓冲区是一个队列，容量超出时去掉开始存入的转移(transition)
+        '''
         if len(self.buffer) < self.capacity:
             self.buffer.append(None)
         self.buffer[self.position] = (state, action, reward, next_state, done)
-        self.position = (self.position + 1) % self.capacity
+        self.position = (self.position + 1) % self.capacity 
     
     def sample(self, batch_size):
-        batch = random.sample(self.buffer, batch_size)
-        state, action, reward, next_state, done =  zip(*batch)
+        batch = random.sample(self.buffer, batch_size) # 随机采出小批量转移
+        state, action, reward, next_state, done =  zip(*batch) # 解压成状态，动作等
         return state, action, reward, next_state, done
-    
-    def __len__(self):
-        return len(self.buffer)
+