policy.py 文件源码

def __init__(self, sess, pred_network, env, dataset, conf):
    self.sess = sess
        self.pred_network = pred_network
        self.env = env
    self.dataset = dataset

    self.ckpt_dir = conf.ckpt_dir 
    self.ckpt_path = conf.ckpt_path
    self.max_iter = conf.max_iter 
    self.max_to_keep = conf.max_to_keep
    self.batch_size = conf.batch_size
    self.df_dim = 64

        self.learning_rate = conf.learning_rate
        self.learning_rate_minimum = conf.learning_rate_minimum
        self.learning_rate_decay = conf.learning_rate_decay
        self.learning_rate_decay_step = conf.learning_rate_decay_step

    self.global_step = tf.get_variable('global_step', [],initializer=tf.constant_initializer(0), trainable=False)

        self.d_bn1 = batch_norm(name='d_bn1')
        self.d_bn2 = batch_norm(name='d_bn2')
        self.d_bn3 = batch_norm(name='d_bn3')
        self.build_opt()