1、引用python库
import tensorflow as tf
from tensorflow.contrib.layers.python.layers import batch_norm as batch_norm
import numpy as np
import math
2、声明参数
# Hyper Parameters
LAYER1_SIZE = 400
LAYER2_SIZE = 300
LEARNING_RATE = 1e-4
TAU = 0.001
BATCH_SIZE = 64
3、定义类
class ActorNetwork:
"""docstring for ActorNetwork"""
def __init__(self,sess,state_dim,action_dim):
(以下全为Class ActorNetwork中的函数)
3.1 初始化函数
def __init__(self,sess,state_dim,action_dim):
self.sess = sess
self.state_dim = state_dim
self.action_dim = action_dim
# create actor network
self.state_input,self.action_output,self.net,self.is_training = self.create_network(state_dim,action_dim)
# create target actor network
self.target_state_input,self.target_action_output,self.target_update,self.target_is_training = self.create_target_network(state_dim,action_dim,self.net)
# define training rules
self.create_training_method()
self.sess.run(tf.initialize_all_variables())
self.update_target()
#self.load_network()
(1)sess表示什么?
(2)赋值了状态、动作的维度
(3)调用create_network()和create_target_network()两个函数,创建了actor网络和target_actor网络
(4)调用函数create_training_method()
(5)调用函数sess.run()
(6)调用函数self.update_target();调用后面三个函数的用途?
3.2其他函数