With the rapid development of next-generation Internet of Things (NG-IoT) networks, the increasing number of connected devices has led to a surge in power consumption. This rise in energy demand poses significant challenges to resource availability and raises sustainability concerns for large-scale IoT deployments. Efficient energy utilization in communication networks, particularly for power-constrained IoT devices, has thus become a critical area of research. In this paper, we deployed flying LoRa gateways (GWs) mounted on unmanned aerial vehicles (UAVs) to collect data from LoRa end devices (EDs) and transmit it to a central server. Our primary objective is to maximize the global system energy efficiency (EE) of wireless LoRa networks by joint optimization of transmission power (TP), spreading factor (SF), bandwidth (W), and ED association. To solve this challenging problem, we model the problem as a partially observable Markov decision process (POMDP), where each flying LoRa GW acts as a learning agent using a cooperative Multi-Agent Reinforcement Learning (MARL) approach under centralized training and decentralized execution (CTDE). Simulation results demonstrate that our proposed method, based on the multi-agent proximal policy optimization (MAPPO) algorithm, significantly improves the global system EE and surpasses the conventional MARL schemes.

This study explores the implementation of large Quantum Restricted Boltzmann Machines (QRBMs), a key advancement in Quantum Machine Learning (QML), as generative models on D-Wave's Pegasus quantum hardware to address dataset imbalance in Intrusion Detection Systems (IDS). By leveraging Pegasus's enhanced connectivity and computational capabilities, a QRBM with 120 visible and 120 hidden units was successfully embedded, surpassing the limitations of default embedding tools. The QRBM synthesized over 1.6 million attack samples, achieving a balanced dataset of over 4.2 million records. Comparative evaluations with traditional balancing methods, such as SMOTE and RandomOversampler, revealed that QRBMs produced higher-quality synthetic samples, significantly improving detection rates, precision, recall, and F1 score across diverse classifiers. The study underscores the scalability and efficiency of QRBMs, completing balancing tasks in milliseconds. These findings highlight the transformative potential of QML and QRBMs as next-generation tools in data preprocessing, offering robust solutions for complex computational challenges in modern information systems.

This paper studies a Markov network model for unbalanced data, aiming to solve the problems of classification bias and insufficient minority class recognition ability of traditional machine learning models in environments with uneven class distribution. By constructing joint probability distribution and conditional dependency, the model can achieve global modeling and reasoning optimization of sample categories. The study introduced marginal probability estimation and weighted loss optimization strategies, combined with regularization constraints and structured reasoning methods, effectively improving the generalization ability and robustness of the model. In the experimental stage, a real credit card fraud detection dataset was selected and compared with models such as logistic regression, support vector machine, random forest and XGBoost. The experimental results show that the Markov network performs well in indicators such as weighted accuracy, F1 score, and AUC-ROC, significantly outperforming traditional classification models, demonstrating its strong decision-making ability and applicability in unbalanced data scenarios. Future research can focus on efficient model training, structural optimization, and deep learning integration in large-scale unbalanced data environments and promote its wide application in practical applications such as financial risk control, medical diagnosis, and intelligent monitoring.

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on atomic propositions associated with the state of a Markov Decision Process (MDP). Our goal is to identify the true reward machine using finite information. To this end, we first introduce the notion of a prefix tree policy which associates a distribution of actions to each state of the MDP and each attainable finite sequence of atomic propositions. Then, we characterize an equivalence class of reward machines that can be identified given the prefix tree policy. Finally, we propose a SAT-based algorithm that uses information extracted from the prefix tree policy to solve for a reward machine. It is proved that if the prefix tree policy is known up to a sufficient (but finite) depth, our algorithm recovers the exact reward machine up to the equivalence class. This sufficient depth is derived as a function of the number of MDP states and (an upper bound on) the number of states of the reward machine. Several examples are used to demonstrate the effectiveness of the approach.

Even highly capable large language models (LLMs) can produce biased or unsafe responses, and alignment techniques, such as RLHF, aimed at mitigating this issue, are expensive and prone to overfitting as they retrain the LLM. This paper introduces a novel inference-time alignment approach that ensures LLMs generate safe responses almost surely, i.e., with a probability approaching one. We achieve this by framing the safe generation of inference-time responses as a constrained Markov decision process within the LLM's latent space. Crucially, we augment a safety state that tracks the evolution of safety constraints and enables us to demonstrate formal safety guarantees upon solving the MDP in the latent space. Building on this foundation, we propose InferenceGuard, a practical implementation that safely aligns LLMs without modifying the model weights. Empirically, we demonstrate InferenceGuard effectively balances safety and task performance, outperforming existing inference-time alignment methods in generating safe and aligned responses.

Value Iteration is a widely used algorithm for solving Markov Decision Processes (MDPs). While previous studies have extensively analyzed its convergence properties, they primarily focus on convergence with respect to the infinity norm. In this work, we use absolute probability sequences to develop a new line of analysis and examine the algorithm's convergence in terms of the $L^2$ norm, offering a new perspective on its behavior and performance.

Flocking control is essential for multi-robot systems in diverse applications, yet achieving efficient flocking in congested environments poses challenges regarding computation burdens, performance optimality, and motion safety. This paper addresses these challenges through a multi-agent reinforcement learning (MARL) framework built on Gibbs Random Fields (GRFs). With GRFs, a multi-robot system is represented by a set of random variables conforming to a joint probability distribution, thus offering a fresh perspective on flocking reward design. A decentralized training and execution mechanism, which enhances the scalability of MARL concerning robot quantity, is realized using a GRF-based credit assignment method. An action attention module is introduced to implicitly anticipate the motion intentions of neighboring robots, consequently mitigating potential non-stationarity issues in MARL. The proposed framework enables learning an efficient distributed control policy for multi-robot systems in challenging environments with success rate around $99\%$, as demonstrated through thorough comparisons with state-of-the-art solutions in simulations and experiments. Ablation studies are also performed to validate the efficiency of different framework modules.

Predicting the future trajectories of surrounding traffic participants plays an essential role in automated driving. By anticipating future movements of nearby agents, such as vehicles and vulnerable road users, an automated vehicle (AV) can better plan maneuvers, reduce the risk of collisions, and ensure smoother interactions with other road users. Although existing approaches, e.g., [1-3], effectively predict the future movements of individual traffic participants, they limit an AV to a reactive planning strategy, assuming that the predictions of surrounding vehicles remain unaffected by the AV's planned actions. In highly interactive situations, this often leads to the freezing robot problem [4], where the AV, unable to engage in cooperative planning, simply stops to avoid potential collisions. For example, when it is unable to merge in dense traffic because the predictions of surrounding vehicles do not react to the AV's plan. One approach to resolving this is to condition the prediction on the AV's plan, often referred to as conditional inference [5].

In this paper, we study an online algorithm in a reproducing kernel Hilbert spaces (RKHS) based on a class of dependent processes, called the mixing process. For such a process, the degree of dependence is measured by various mixing coefficients. As a representative example, we analyze a strictly stationary Markov chain, where the dependence structure is characterized by the \(\beta-\) and \(\phi-\)mixing coefficients. For these dependent samples, we derive nearly optimal convergence rates. Our findings extend existing error bounds for i.i.d. observations, demonstrating that the i.i.d. case is a special instance of our framework. Moreover, we explicitly account for an additional factor introduced by the dependence structure in the Markov chain.

Multi-agent reinforcement learning typically employs a centralized training-decentralized execution (CTDE) framework to alleviate the non-stationarity in environment. However, the partial observability during execution may lead to cumulative gap errors gathered by agents, impairing the training of effective collaborative policies. To overcome this challenge, we introduce the Double Distillation Network (DDN), which incorporates two distillation modules aimed at enhancing robust coordination and facilitating the collaboration process under constrained information. The external distillation module uses a global guiding network and a local policy network, employing distillation to reconcile the gap between global training and local execution. In addition, the internal distillation module introduces intrinsic rewards, drawn from state information, to enhance the exploration capabilities of agents. Extensive experiments demonstrate that DDN significantly improves performance across multiple scenarios.