reagent/evaluation/evaluation_data_page.py [276:297]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        trainer.q_network.train(old_q_train_state)
        trainer.reward_network.train(old_reward_train_state)

        return cls(
            mdp_id=mdp_ids,
            sequence_number=sequence_numbers,
            logged_propensities=propensities,
            logged_rewards=rewards,
            action_mask=action_mask,
            model_rewards=model_rewards,
            model_rewards_for_logged_action=model_rewards_for_logged_action,
            model_values=model_values,
            model_metrics_values=model_metrics_values,
            model_metrics_values_for_logged_action=model_metrics_values_for_logged_action,
            model_propensities=model_propensities,
            logged_metrics=metrics,
            model_metrics=model_metrics,
            model_metrics_for_logged_action=model_metrics_for_logged_action,
            # Will compute later
            logged_values=None,
            logged_metrics_values=None,
            possible_actions_mask=possible_actions_mask,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



reagent/evaluation/evaluation_data_page.py [430:453]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        trainer.q_network.train(old_q_train_state)
        # pyre-fixme[16]: Item `Tensor` of `Union[Tensor, Module]` has no attribute
        #  `train`.
        trainer.reward_network.train(old_reward_train_state)

        return cls(
            mdp_id=mdp_ids,
            sequence_number=sequence_numbers,
            logged_propensities=propensities,
            logged_rewards=rewards,
            action_mask=action_mask,
            model_rewards=model_rewards,
            model_rewards_for_logged_action=model_rewards_for_logged_action,
            model_values=model_values,
            model_metrics_values=model_metrics_values,
            model_metrics_values_for_logged_action=model_metrics_values_for_logged_action,
            model_propensities=model_propensities,
            logged_metrics=metrics,
            model_metrics=model_metrics,
            model_metrics_for_logged_action=model_metrics_for_logged_action,
            # Will compute later
            logged_values=None,
            logged_metrics_values=None,
            possible_actions_mask=possible_actions_mask,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -