tf_agents/bandits/agents/greedy_multi_objective_neural_agent.py [192:211]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    variables_to_train = self._variables_to_train()
    if not variables_to_train:
      logging.info('No variable to train in the agent.')
      return loss_info

    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 = tuple(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:
      eager_utils.add_variables_summaries(grads_and_vars,
                                          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)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/bandits/agents/greedy_reward_prediction_agent.py [223:242]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    variables_to_train = self._variables_to_train()
    if not variables_to_train:
      logging.info('No variable to train in the agent.')
      return loss_info

    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 = tuple(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:
      eager_utils.add_variables_summaries(grads_and_vars,
                                          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)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -