【tensorflow】【python】tf.gradients

tf.gradients

语法

tf.gradients(ys, 
             xs, 
			 grad_ys=None, 
			 name='gradients',
			 colocate_gradients_with_ops=False,
			 gate_gradients=False,
			 aggregation_method=None,
			 stop_gradients=None)

tf.gradients(
    ys,
    xs,
    grad_ys=None,
    name='gradients',
    gate_gradients=False,
    aggregation_method=None,
    stop_gradients=None,
    unconnected_gradients=tf.UnconnectedGradients.NONE
)

含义

ys对xs进行求导
$\left[\frac{\partial y}{\partial x}\right]$

$\left[\frac{\partial ys}{\partial xs}\right]$

示例

self.a_grads = tf.gradients(self.a_loss, self.a_params)
self.c_grads = tf.gradients(self.c_loss, self.c_params)

Actor网络的损失函数a_loss关于Actor网络参数a_params求梯度：
ys1 = a_loss
xs1 = a_params

Critic网络的损失函数c_loss关于Critic网络参数c_params求梯度：
ys2 = c_loss
xs2 = c_params

https://tensorflow.google.cn/api_docs/python/tf/gradients?hl=en

$\left|\frac{\partial \mathrm{loss}}{\partial \mathrm{local}\_\mathrm{q}}\right]$

q_gradients = tf.gradients(loss, local_q)