def create_net(self, shape):
hidden_size = 64
print(shape)
self.x = tf.placeholder(tf.float32, shape=[None, shape], name="x")
self.y = tf.placeholder(tf.float32, shape=[None], name="y")
weight_init = tf.random_uniform_initializer(-0.05, 0.05)
bias_init = tf.constant_initializer(0)
with tf.variable_scope("VF"):
h1 = tf.nn.relu(fully_connected(self.x, shape, hidden_size, weight_init, bias_init, "h1"))
h2 = tf.nn.relu(fully_connected(h1, hidden_size, hidden_size, weight_init, bias_init, "h2"))
h3 = fully_connected(h2, hidden_size, 1, weight_init, bias_init, "h3")
self.net = tf.reshape(h3, (-1,))
l2 = tf.nn.l2_loss(self.net - self.y)
self.train = tf.train.AdamOptimizer().minimize(l2)
self.session.run(tf.initialize_all_variables())
value_function.py 文件源码
python
阅读 27
收藏 0
点赞 0
评论 0
评论列表
文章目录