def get_mu_sigma(self):
with tf.variable_scope('actor'):
w_i = tf.random_uniform_initializer(0., 0.1)
dense1 = dense(self.state_input, 200, None, w_i, None, activation=tf.nn.relu6)
with tf.variable_scope('mu'):
mu = dense(dense1, self.action_dim, None, w_i, None, activation=tf.nn.tanh)
with tf.variable_scope('sigma'):
sigma = dense(dense1, self.action_dim, None, w_i, None, activation=tf.nn.softplus)
# return mu * self.config.ACTION_BOUND[1], sigma + 1e-4
return mu, sigma + 1e-4
评论列表
文章目录