Theoretical Foundations of the Dual Control Algorithm for Multi-Agent Information-Measuring Systems

This article examines the theoretical foundations of the dual control algorithm in the context of machine learning, focusing on its application for intelligent agents in multi-agent information-measuring systems. A proposed algorithm combines anomaly detection in data with telemetry-based sensor calibration, opening new possibilities for improving the accuracy and reliability of data in complex and dynamic environments. The advantages of the algorithm are analyzed concerning adaptability, forecasting, and data integration, comparing it with other machine learning algorithms. A scheme of the software algorithm for the sensor data acquisition module is presented. A machine learning model of the dual control algorithm is developed and compared with the isolation forest model, highlighting the advantages of applying the dual control algorithm for building multi-agent information-measuring systems.