tf_agents/agents/dqn/dqn_agent.py [393:418]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
          weights=weights,
          training=True)
    tf.debugging.check_numerics(loss_info.loss, 'Loss is inf or nan')
    variables_to_train = self._q_network.trainable_weights
    non_trainable_weights = self._q_network.non_trainable_weights
    assert list(variables_to_train), "No variables in the agent's q_network."
    grads = tape.gradient(loss_info.loss, variables_to_train)
    # Tuple is used for py3, where zip is a generator producing values once.
    grads_and_vars = list(zip(grads, variables_to_train))
    if self._gradient_clipping is not None:
      grads_and_vars = eager_utils.clip_gradient_norms(grads_and_vars,
                                                       self._gradient_clipping)

    if self._summarize_grads_and_vars:
      grads_and_vars_with_non_trainable = (
          grads_and_vars + [(None, v) for v in non_trainable_weights])
      eager_utils.add_variables_summaries(grads_and_vars_with_non_trainable,
                                          self.train_step_counter)
      eager_utils.add_gradients_summaries(grads_and_vars,
                                          self.train_step_counter)
    self._optimizer.apply_gradients(grads_and_vars)
    self.train_step_counter.assign_add(1)

    self._update_target()

    return loss_info
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/agents/qtopt/qtopt_agent.py [499:526]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
          weights=weights,
          training=True)

    tf.debugging.check_numerics(loss_info.loss, 'Loss is inf or nan')
    variables_to_train = self._q_network.trainable_weights

    non_trainable_weights = self._q_network.non_trainable_weights
    assert list(variables_to_train), "No variables in the agent's q_network."
    grads = tape.gradient(loss_info.loss, variables_to_train)
    # Tuple is used for py3, where zip is a generator producing values once.
    grads_and_vars = list(zip(grads, variables_to_train))
    if self._gradient_clipping is not None:
      grads_and_vars = eager_utils.clip_gradient_norms(grads_and_vars,
                                                       self._gradient_clipping)

    if self._summarize_grads_and_vars:
      grads_and_vars_with_non_trainable = (
          grads_and_vars + [(None, v) for v in non_trainable_weights])
      eager_utils.add_variables_summaries(grads_and_vars_with_non_trainable,
                                          self.train_step_counter)
      eager_utils.add_gradients_summaries(grads_and_vars,
                                          self.train_step_counter)
    self._optimizer.apply_gradients(grads_and_vars)
    self.train_step_counter.assign_add(1)

    self._update_target()

    return loss_info
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -