代码小调，增加readme

Author: “yezhenbin

PER-and-ACQ/net.py

@@ -1,6 +1,7 @@
 import torch
 from torch import nn
 
+
 class AtariNet(nn.Module):
 
     def __init__(self, num_actions):

PER-and-ACQ/util.py

@@ -1,6 +1,13 @@
 import cv2
 import numpy as np
+
+
 def preprocess(observation):
+    """
+    image preprocess
+    :param observation:
+    :return:
+    """
     observation = cv2.cvtColor(cv2.resize(observation, (84, 110)), cv2.COLOR_BGR2GRAY)
     observation = observation[26:110,:]
     ret, observation = cv2.threshold(observation,1,255,cv2.THRESH_BINARY)

README.md

@@ -26,4 +26,10 @@ ddpg.py
 
 ## 10.1.2 A3C DDPG：
 
-A3C-DDPG.py
+A3C-DDPG.py
+
+## 联系作者
+
+### 邮箱：[email protected]
+
+### 代码持续更新，您若有改进建议或者问题请联系作者

ddpg.py

@@ -30,8 +30,10 @@ def sample(self, batch_size):
             d.append(np.array(D, copy=False))
         return np.array(x), np.array(y), np.array(u), np.array(r).reshape(-1, 1), np.array(d).reshape(-1, 1)
 
+
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+
 class Actor(nn.Module):
     def __init__(self, state_dim, action_dim, max_action):
         super(Actor, self).__init__()

double-DQN.py

@@ -71,6 +71,7 @@ def learn(self, state, action, reward, next_state, done):
         loss.backward()
         self.optimizer.step()
 
+
 agent = Agent()
 
 for i_episode in range(TOTAL_EPISODES):

dueling-DQN.py

@@ -124,6 +124,7 @@ def learn(self, state, action, reward, next_state, done):
         loss.backward()
         self.optimizer.step()
 
+
 agent = Agent()
 
 for i_episode in range(TOTAL_EPISODES):

nature-DQN.py

@@ -69,6 +69,7 @@ def learn(self, state, action, reward, next_state, done):
         loss.backward()
         self.optimizer.step()
 
+
 agent = Agent()
 
 for i_episode in range(TOTAL_EPISODES):

net.py

@@ -1,6 +1,7 @@
 import torch
 from torch import nn
 
+
 class AtariNet(nn.Module):
 
     def __init__(self, num_actions):

nips-DQN.py

@@ -63,6 +63,7 @@ def learn(self, state, action, reward, next_state, done):
         loss.backward()
         self.optimizer.step()
 
+
 agent = Agent()
 
 for i_episode in range(TOTAL_EPISODES):

util.py

@@ -1,6 +1,13 @@
 import cv2
 import numpy as np
+
+
 def preprocess(observation):
+    """
+    image preprocess
+    :param observation:
+    :return:
+    """
     observation = cv2.cvtColor(cv2.resize(observation, (84, 110)), cv2.COLOR_BGR2GRAY)
     observation = observation[26:110,:]
     ret, observation = cv2.threshold(observation,1,255,cv2.THRESH_BINARY)