reagent/model_managers/discrete/discrete_crr.py [132:155]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        reward_options = reward_options or RewardOptions()
        metrics_to_score = get_metrics_to_score(reward_options.metric_reward_values)

        reward_network, q_network_cpe, q_network_cpe_target = None, None, None
        if self.eval_parameters.calc_cpe_in_training:
            # Metrics + reward
            num_output_nodes = (len(metrics_to_score) + 1) * len(
                # pyre-fixme[16]: `CRRTrainerParameters` has no attribute `actions`.
                self.trainer_param.actions
            )

            cpe_net_builder = self.cpe_net_builder.value
            reward_network = cpe_net_builder.build_q_network(
                self.state_feature_config,
                normalization_data_map[NormalizationKey.STATE],
                num_output_nodes,
            )
            q_network_cpe = cpe_net_builder.build_q_network(
                self.state_feature_config,
                normalization_data_map[NormalizationKey.STATE],
                num_output_nodes,
            )

            q_network_cpe_target = q_network_cpe.get_target_network()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



reagent/model_managers/discrete/discrete_qrdqn.py [76:99]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        reward_options = reward_options or RewardOptions()
        metrics_to_score = get_metrics_to_score(reward_options.metric_reward_values)

        reward_network, q_network_cpe, q_network_cpe_target = None, None, None
        if self.eval_parameters.calc_cpe_in_training:
            # Metrics + reward
            num_output_nodes = (len(metrics_to_score) + 1) * len(
                # pyre-fixme[16]: `QRDQNTrainerParameters` has no attribute `actions`.
                self.trainer_param.actions
            )

            cpe_net_builder = self.cpe_net_builder.value
            reward_network = cpe_net_builder.build_q_network(
                self.state_feature_config,
                normalization_data_map[NormalizationKey.STATE],
                num_output_nodes,
            )
            q_network_cpe = cpe_net_builder.build_q_network(
                self.state_feature_config,
                normalization_data_map[NormalizationKey.STATE],
                num_output_nodes,
            )

            q_network_cpe_target = q_network_cpe.get_target_network()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -