In this paper, a data-driven control scheme is proposed by integrating both reinforcement learning (RL) and iterative learning control (ILC) methodologies. To address the limitations of conventional ILC and extend its applicability, a new approach called Forgetting Factor ILC (FFILC) has been introduced. The FFILC exhibits improved performance in the presence of non-repetitive noise, disturbances, and system uncertainties compared to traditional ILC. This improvement is attributed to its ability to incorporate past data, enhancing adaptability to changing conditions. RL is utilized to determine the optimal forgetting factor. During initial iterations, larger errors are common, and a dynamic forgetting factor expedites convergence. In addition, RL equips the system with intelligence, facilitating superior adaptive performance and resilience as the environment changes throughout iterations. The paper provides a mathematical proof to analyze the convergence of RL-FFILC. Simulations involving a quadrotor system and a drum-type boiler turbine plant demonstrate the superior performance of RL-FFILC compared to some advanced control methods. Note to Practitioners—Industrial automation frequently involves repetitive processes, for which ILC is a suitable method to enhance performance. However, conventional ILC methods can be limited by special systems, non-repetitive disturbances and noise. For practitioners, RL-FFILC, as an intelligent robust control, offers a practical solution to enhance control performance in dynamic settings. This method is data-driven, meaning it does not require accurate model identification prior to implementation, making it suitable for applications where obtaining precise system models is difficult or impractical. The effectiveness of RL-FFILC is demonstrated through simulations on two distinct systems, a quadrotor and a drum-type boiler turbine plant. The quadrotor, an autonomous system with six degrees of freedom, showcases the method’s applicability to other autonomous systems with similar or fewer degrees of freedom. The drum-type boiler turbine plant, crucial in many industrial processes, highlights the relevance of the method in maintaining system stability and efficiency despite variable operational conditions. These applications fall within Cyber-Physical Systems (CPS), where intelligent data-driven control enhances adaptability and resilience.

Abstract Today, the development of urbanization and increasing the number of vehicles has resulted in displeased consequences like traffic congestion and vehicle queuing. The vast majority of countries in the world encounter the challenge of the explosive rise in traffic demand. In this regard, it is necessary to meet traffic demand in transport networks, especially in metropolitans. In traffic management and shortening the trip duration, traffic lights on the signalized intersections play an essential role in urban pathways. This work provides a multi‐criteria decision‐making method for optimum traffic light control in an isolated corner. The main idea involves establishing a set of sub‐optimal solutions for traffic light timing and selecting the best one among the diverse solutions. We have mathematically modelled the problem as an optimization problem to achieve an optimal solution with less waiting time for vehicles in intersections and the lowest cost. Genetic algorithm (GA) and Teaching‐Learning‐based Optimization (TLBO) are utilized for each phase to create a set of suitable timing scenarios. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method is used to identify the best scenario, considering both waiting vehicles and traffic capacity as decision criteria. Its efficiency has been demonstrated over three different traffic volumes. Also, in a real‐world implementation, its practical capability has been approved at a crossroads in Mashhad, Iran. The simulations indicate the improvement in the number of vehicles waiting behind the crossroad and the traffic capacity by 10% and 6.76% compared to the existing signal timing of the studied intersection, respectively.