This paper introduces a novel framework that bridges advanced reinforcement learning (RL) with traditional PID control by converting model-based RL policies into interpretable PID gains. By combining inverse reinforcement learning (IRL) with Kullback–Leibler divergence minimization, our method aligns sophisticated control strategies with the simplicity and robustness of PID controllers. In doing so, the proposed approach maintains the transparency and simplicity of PID controllers while incorporating the adaptability, data-driven optimization, and long-horizon planning capabilities of RL. Compatible with both model-based and model-free RL algorithms, the approach has been validated through extensive simulations on benchmark systems and real-world experiments on the Robotarium platform, demonstrating resilience against disturbances, parameter uncertainties, and noise. By blending the strengths of reinforcement learning with the practical familiarity of PID control, the proposed framework offers a data-efficient, scalable, and transparent solution for enhancing PID controller design in complex and dynamic environments.

In this paper, we explore the stabilization of Boolean Networks (BNs) under state-flipped control, incorporating three key constraints to address the challenges of disease treatment response times and the practical limitations of therapeutic interventions. Our approach includes: (i) a feasible flipped nodes constraint to ensure a subset of nodes can be realistically manipulated; (ii) a transient period constraint to align treatment with time-sensitive windows of therapeutic opportunity; and (iii) a constraint on the number of flip transitions to minimize resource consumption and potential side effects. Furthermore, an evolution selection rule is set for the BNs. Then, a necessary and sufficient condition is given for the stabilization under the above constraints. We present a modified Q-learning (QL) algorithm to design a policy for stabilization under constraints in the model-free case. Finally, BN models of metastatic melanoma network and T-cell large granular lymphocyte (T-LGL) network are considered to show the applicability of our results.

Boolean Networks (BNs) are a powerful model to describe how gene work and holistically interact with one another in system biology. Based on the requirement to guide the systems to a desired state, the stabilization problem becomes an important issue in BNs. Since the normal state feedback control puts controllers to all nodes, the control cost is relatively high. In this paper, we investigate the stabilization problem of BNs under pinning control strategy. Meanwhile, to cut down the cost of control to the most, the set of pinned nodes is minimized. Specifically, a four-procedure method as well as the corresponding computationally feasible algorithms are proposed to determine a minimum set of controlled nodes based on a deformed state transition matrix and a constructed digraph. Compared with the strategy traditionally based on the state transition matrix, the approach we proposed effectively reduces the computational complexity. Finally, gene networks are discussed as simulations, which demonstrate the effectiveness of the proposed method, minimizing the number of controlled nodes with lower time complexity.

In this article, set stabilization in switched Boolean networks is investigated through link augmentations. Link augmentation is introduced as a selective process for adding specific edges between nodes in the wiring digraph of the network. For the implementation of link augmentation, various variables are integrated into the dynamics governing networks, utilizing basic logical operators. A key aspect of this article is the incorporation of additional functions introduced by the link augmentations into the original dynamics of the system using constrained logical operators. Further, several criteria for set stabilization are formulated, and the link augmentation control strategy is innovatively designed, utilizing theQ-learning Algorithm. Finally, a biological example is presented to demonstrate the effectiveness of the proposed methods.

This article develops pinning control strategies to achieve global asymptotic stabilization in large-scale Markovian jump Boolean networks (MJBNs), closely linking their stability to network structural characteristics. First, the considered MJBN is divided into several sub-MJBNs, where signals switch according to irreducible transition probability matrices. Second, the stability of these sub-MJBNs is mapped onto that of deterministic periodic BNs. This transformation facilitates the formulation of a network-structure-based stability criterion for MJBNs by converting the inherently random stability characteristics of the networks into those of deterministic networks. Third, applying this criterion, static pinning control (SPC) is devised to stabilize MJBNs, where effective pinning nodes are identified by finding a feedback vertex set in the correspondingn-vertex digraph. Consequently, this method addresses the challenges associated with large-scale MJBNs effectively. To demonstrate the practical applicability of our theoretical findings, two biological examples are presented.

On the verge of technology, manufacturing industries revolutionize into smart industries, which create a large amount of multivariate time-series data. However, due to sensors’ failure, extreme environment, etc., the collected data are incomplete and have missing values at several instances that result in an erroneous analysis of the data. The key to resolving this problem is data imputation, i.e., replacing the missing values with synthetic values. In this paper, we introduce a generative adversarial network (GAN) framework to generate the synthetic data pertaining to the data imputation. Over the last decade, GANs have presented excellent results to generate synthetic data for images. By following this stream of research, we consider multivariate time-series data from a steel manufacturing industry and propose a GAN-based data imputation technique. We perform several computer simulations to validate and compare the performance of the proposed GAN method with state-of-the-art data imputation techniques.

In this paper, we propose a novel random forest (RF) Q-learning hybrid with experience replay for feedback stabilization of probabilistic Boolean control networks (PBCNs). In particular, by resorting to a model-free reinforcement learning (RL) framework, we present a random forest Q-learning (QLRF) algorithm to design optimal state feedback controllers, thereby stabilizing PBCNs to a given equilibrium point. In reference to better the process of learning the Q-table by replacing it with a function approximator, we substitute the existent neural network (NN) architecture by a RF. We provide insights on the overall computational complexity between the two ways of solving the same problem, proving RF better than its NN counterparts for such applications. The simulations performed on some of the standard examples in the literature demonstrates the effectiveness of the proposed idea.

Utility companies are an integral part of the smart grid, providing consumers with a broad range of energy management programs. The quality of service is based on the measurements obtained from smart metering infrastructures, which can further be improved by sensing at finer resolutions. However, sensing at higher resolutions poses serious challenges both in terms of storage and communication overload due to overgrowing traffic. Compressive sensing is a data compression technique that accounts for the sparsity of electricity consumption pattern in a transformation basis and achieves subNyquist compression. To the best of the authors' knowledge, this is the first study to use the semi-tensor product (STP) for compressed sensing (CS) of power consumption data in the smart grid. In contrast to the conventional CS, the proposed approach has the advantage of reducing the dimension of the sensing matrix needed to sense the signal, thereby significantly lowering the storage requirements. In this regard, we present a comparative study highlighting the difference in compression performance with the conventional CS and STP based CS, where the transformation basis used is Haar and Hankel. We present the results on three publicly available datasets at different sampling rates and outline the key findings of the study.

Probabilistic Boolean control network (PBCN) is a discrete-time dynamical system comprised of a collection of Boolean control networks (BCNs) and switching among them in a stochastic manner. In this paper, the output tracking control of PBCNs is investigated via state feedback and output feedback control. By resorting to the algebraic state-space representation of BCNs, necessary and sufficient conditions for the solvability of the output tracking control problem are presented. A constructive procedure is given to obtain all possible state feedback and output feedback controllers such that the output of PBCNs tracks a constant reference signal. Finally, a PBCN model of a simple manufacturing system is considered to illustrate the effectiveness of the proposed results.