agent.py 文件源码

def __make_net(self, input_images, input_measure, input_actions, reuse=False):
        if reuse:
            tf.get_variable_scope().reuse_variables()
        fc_val_params = copy.deepcopy(self.__fc_joint_params)
        fc_val_params[-1]['out_dims'] = self.__target_dim

        fc_adv_params = copy.deepcopy(self.__fc_joint_params)
        fc_adv_params[-1]['out_dims'] = len(self.__net_discrete_actions) * self.__target_dim

        if self.verbose:
            print 'fc_val_params:', fc_val_params
            print 'fc_adv_params:', fc_adv_params

        p_img_conv = ly.conv_encoder(input_images, self.__conv_params, 'p_img_conv', msra_coeff=0.9)
        p_img_fc = ly.fc_net(ly.flatten(p_img_conv), self.__fc_img_params, 'p_img_fc', msra_coeff=0.9)
        p_meas_fc = ly.fc_net(input_measure, self.__fc_measure_params, 'p_meas_fc', msra_coeff=0.9)
        p_val_fc = ly.fc_net(tf.concat([p_img_fc, p_meas_fc], 1),
                             fc_val_params, 'p_val_fc', last_linear=True, msra_coeff=0.9)
        p_adv_fc = ly.fc_net(tf.concat([p_img_fc, p_meas_fc], 1),
                             fc_adv_params, 'p_adv_fc', last_linear=True, msra_coeff=0.9)
        p_adv_fc_nomean = p_adv_fc - tf.reduce_mean(p_adv_fc, reduction_indices=1, keep_dims=True)

        self.__pred_all_nomean = tf.reshape(p_adv_fc_nomean, [-1, len(self.__net_discrete_actions), self.__target_dim])
        self.__pred_all = self.__pred_all_nomean + tf.reshape(p_val_fc, [-1, 1, self.__target_dim])
        self.__pred_relevant = tf.boolean_mask(self.__pred_all, tf.cast(input_actions, tf.bool))