def update_priorities(self, traces_idxs, td_errors):
"""Updates the priorities of the traces with specified indexes."""
self.priorities[traces_idxs] = td_errors + eps
我试过用
tf.py_function
调用包装器函数,但只有当它嵌入到图中(即,如果它有输入和输出,并且使用输出)时才会调用它。因此,我试图通过一些张量而不对它们执行任何操作,函数现在被调用。以下是我的整个自定义丢失功能:
def masked_q_loss(data, y_pred):
"""Computes the MSE between the Q-values of the actions that were taken and the cumulative
discounted rewards obtained after taking those actions. Updates trace priorities.
"""
action_batch, target_qvals, traces_idxs = data[:,0], data[:,1], data[:,2]
seq = tf.cast(tf.range(0, tf.shape(action_batch)[0]), tf.int32)
action_idxs = tf.transpose(tf.stack([seq, tf.cast(action_batch, tf.int32)]))
qvals = tf.gather_nd(y_pred, action_idxs)
def update_priorities(_qvals, _target_qvals, _traces_idxs):
"""Computes the TD error and updates memory priorities."""
td_error = _target_qvals - _qvals
_traces_idxs = tf.cast(_traces_idxs, tf.int32)
mem.update_priorities(_traces_idxs, td_error)
return _qvals
qvals = tf.py_function(func=update_priorities, inp=[qvals, target_qvals, traces_idxs], Tout=[tf.float32])
return tf.keras.losses.mse(qvals, target_qvals)
但是,由于调用,我得到以下错误
mem.update_priorities(_traces_idxs, td_error)
ValueError: An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.
我不需要计算梯度
update_priorities
,我只想在图形计算中的特定点调用它,而忽略它。我该怎么做?