Adaptive Traffic Signal Control (ATSC) system is a critical component of intelligent transportation, with the capability to significantly alleviate urban traffic congestion. Although reinforcement learning (RL)-based methods have demonstrated promising performance in achieving ATSC, existing methods are still prone to making unreasonable policies. Therefore, this paper proposes a novel Bayesian Critique-Tune-Based Reinforcement Learning with Adaptive Pressure for multi-intersection signal control (BCT-APLight). In BCT-APLight, the Critique-Tune (CT) framework, a two-layer Bayesian structure is designed to refine the excessive trust of RL policies. Specifically, the Bayesian inference-based Critique Layer provides effective evaluations of the credibility of policies; the Bayesian decision-based Tune Layer fine-tunes policies by minimizing the posterior risks when the evaluations are negative. Meanwhile, an attention-based Adaptive Pressure (AP) mechanism is designed to effectively weight the vehicle queues in each lane, thereby enhancing the rationality of traffic movement representation within the network. Equipped with the CT framework and AP mechanism, BCT-APLight effectively enhances the reasonableness of RL policies. Extensive experiments conducted with a simulator across a range of intersection layouts demonstrate that BCT-APLight is superior to other state-of-the-art (SOTA) methods on seven real-world datasets. Specifically, BCT-APLight decreases average queue length by \textbf{\(\boldsymbol{9.60\%}\)} and average waiting time by \textbf{\(\boldsymbol{15.28\%}\)}.

In many practical applications, decision-making processes must balance the costs of acquiring information with the benefits it provides. Traditional control systems often assume full observability, an unrealistic assumption when observations are expensive. We tackle the challenge of simultaneously learning observation and control strategies in such cost-sensitive environments by introducing the Observation-Constrained Markov Decision Process (OCMDP), where the policy influences the observability of the true state. To manage the complexity arising from the combined observation and control actions, we develop an iterative, model-free deep reinforcement learning algorithm that separates the sensing and control components of the policy. This decomposition enables efficient learning in the expanded action space by focusing on when and what to observe, as well as determining optimal control actions, without requiring knowledge of the environment's dynamics. We validate our approach on a simulated diagnostic task and a realistic healthcare environment using HeartPole. Given both scenarios, the experimental results demonstrate that our model achieves a substantial reduction in observation costs on average, significantly outperforming baseline methods by a notable margin in efficiency.

In multi-agent reinforcement learning, a commonly considered paradigm is centralized training with decentralized execution. However, in this framework, decentralized execution restricts the development of coordinated policies due to the local observation limitation. In this paper, we consider the cooperation among neighboring agents during execution and formulate their interactions as a graph. Thus, we introduce a novel encoder-decoder architecture named Factor-based Multi-Agent Transformer ($f$-MAT) that utilizes a transformer to enable communication between neighboring agents during both training and execution. By dividing agents into different overlapping groups and representing each group with a factor, $f$-MAT achieves efficient message passing and parallel action generation through factor-based attention layers. Empirical results in networked systems such as traffic scheduling and power control demonstrate that $f$-MAT achieves superior performance compared to strong baselines, thereby paving the way for handling complex collaborative problems.

In multi-agent reinforcement learning (MARL), the centralized training with decentralized execution (CTDE) framework has gained widespread adoption due to its strong performance. However, the further development of CTDE faces two key challenges. First, agents struggle to autonomously assess the relevance of input information for cooperative tasks, impairing their decision-making abilities. Second, in communication-limited scenarios with partial observability, agents are unable to access global information, restricting their ability to collaborate effectively from a global perspective. To address these challenges, we introduce a novel cooperative MARL framework based on information selection and tacit learning. In this framework, agents gradually develop implicit coordination during training, enabling them to infer the cooperative behavior of others in a discrete space without communication, relying solely on local information. Moreover, we integrate gating and selection mechanisms, allowing agents to adaptively filter information based on environmental changes, thereby enhancing their decision-making capabilities. Experiments on popular MARL benchmarks show that our framework can be seamlessly integrated with state-of-the-art algorithms, leading to significant performance improvements.

Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects through two experimental setups: supervised learning with NLP tasks (NLP-SL) and deep reinforcement learning for traffic signal optimization (Signal-RL). We analyze the relationship between data corruption levels and model performance, evaluate the effectiveness of data imputation methods, and assess the utility of enlarging datasets to address data corruption. Our results show that model performance under data corruption follows a diminishing return curve, modeled by the exponential function. Missing data, while detrimental, is less harmful than noisy data, which causes severe performance degradation and training instability, particularly in sequential decision-making tasks like Signal-RL. Imputation strategies involve a trade-off: they recover missing information but may introduce noise. Their effectiveness depends on imputation accuracy and corruption ratio. We identify distinct regions in the imputation advantage heatmap, including an "imputation advantageous corner" and an "imputation disadvantageous edge" and classify tasks as "noise-sensitive" or "noise-insensitive" based on their decision boundaries. Furthermore, we find that increasing dataset size mitigates but cannot fully overcome the effects of data corruption. The marginal utility of additional data diminishes as corruption increases. An empirical rule emerges: approximately 30% of the data is critical for determining performance, while the remaining 70% has minimal impact. These findings provide actionable insights into data preprocessing, imputation strategies, and data collection practices, guiding the development of robust machine learning systems in noisy environments.

In compute-first networking, maintaining fresh and accurate status information at the network edge is crucial for effective access to remote services. This process typically involves three phases: Status updating, user accessing, and user requesting. However, current studies on status effectiveness, such as Age of Information at Query (QAoI), do not comprehensively cover all these phases. Therefore, this paper introduces a novel metric, TPAoI, aimed at optimizing update decisions by measuring the freshness of service status. The stochastic nature of edge environments, characterized by unpredictable communication delays in updating, requesting, and user access times, poses a significant challenge when modeling. To address this, we model the problem as a Markov Decision Process (MDP) and employ a Dueling Double Deep Q-Network (D3QN) algorithm for optimization. Extensive experiments demonstrate that the proposed TPAoI metric effectively minimizes AoI, ensuring timely and reliable service updates in dynamic edge environments. Results indicate that TPAoI reduces AoI by an average of 47\% compared to QAoI metrics and decreases update frequency by an average of 48\% relative to conventional AoI metrics, showing significant improvement.

The availability of challenging simulation environments is pivotal for advancing the field of Multi-Agent Reinforcement Learning (MARL). In cooperative MARL settings, the StarCraft Multi-Agent Challenge (SMAC) has gained prominence as a benchmark for algorithms following centralized training with decentralized execution paradigm. However, with continual advancements in SMAC, many algorithms now exhibit near-optimal performance, complicating the evaluation of their true effectiveness. To alleviate this problem, in this work, we highlight a critical issue: the default opponent policy in these environments lacks sufficient diversity, leading MARL algorithms to overfit and exploit unintended vulnerabilities rather than learning robust strategies. To overcome these limitations, we propose SMAC-HARD, a novel benchmark designed to enhance training robustness and evaluation comprehensiveness. SMAC-HARD supports customizable opponent strategies, randomization of adversarial policies, and interfaces for MARL self-play, enabling agents to generalize to varying opponent behaviors and improve model stability. Furthermore, we introduce a black-box testing framework wherein agents are trained without exposure to the edited opponent scripts but are tested against these scripts to evaluate the policy coverage and adaptability of MARL algorithms. We conduct extensive evaluations of widely used and state-of-the-art algorithms on SMAC-HARD, revealing the substantial challenges posed by edited and mixed strategy opponents. Additionally, the black-box strategy tests illustrate the difficulty of transferring learned policies to unseen adversaries. We envision SMAC-HARD as a critical step toward benchmarking the next generation of MARL algorithms, fostering progress in self-play methods for multi-agent systems. Our code is available at https://github.com/devindeng94/smac-hard.

Deep reinforcement learning (DRL) shows promising potential for autonomous driving decision-making. However, DRL demands extensive computational resources to achieve a qualified policy in complex driving scenarios due to its low learning efficiency. Moreover, leveraging expert guidance from human to enhance DRL performance incurs prohibitively high labor costs, which limits its practical application. In this study, we propose a novel large language model (LLM) guided deep reinforcement learning (LGDRL) framework for addressing the decision-making problem of autonomous vehicles. Within this framework, an LLM-based driving expert is integrated into the DRL to provide intelligent guidance for the learning process of DRL. Subsequently, in order to efficiently utilize the guidance of the LLM expert to enhance the performance of DRL decision-making policies, the learning and interaction process of DRL is enhanced through an innovative expert policy constrained algorithm and a novel LLM-intervened interaction mechanism. Experimental results demonstrate that our method not only achieves superior driving performance with a 90\% task success rate but also significantly improves the learning efficiency and expert guidance utilization efficiency compared to state-of-the-art baseline algorithms. Moreover, the proposed method enables the DRL agent to maintain consistent and reliable performance in the absence of LLM expert guidance. The code and supplementary videos are available at https://bitmobility.github.io/LGDRL/.

Millimeter wave (mmWave)-based orthogonal frequency-division multiplexing (OFDM) stands out as a suitable alternative for high-resolution sensing and high-speed data transmission. To meet communication and sensing requirements, many works propose a static configuration where the wave's hyperparameters such as the number of symbols in a frame and the number of frames in a communication slot are already predefined. However, two facts oblige us to redefine the problem, (1) the environment is often dynamic and uncertain, and (2) mmWave is severely impacted by wireless environments. A striking example where this challenge is very prominent is autonomous vehicle (AV). Such a system leverages integrated sensing and communication (ISAC) using mmWave to manage data transmission and the dynamism of the environment. In this work, we consider an autonomous vehicle network where an AV utilizes its queue state information (QSI) and channel state information (CSI) in conjunction with reinforcement learning techniques to manage communication and sensing. This enables the AV to achieve two primary objectives: establishing a stable communication link with other AVs and accurately estimating the velocities of surrounding objects with high resolution. The communication performance is therefore evaluated based on the queue state, the effective data rate, and the discarded packets rate. In contrast, the effectiveness of the sensing is assessed using the velocity resolution. In addition, we exploit adaptive OFDM techniques for dynamic modulation, and we suggest a reward function that leverages the age of updates to handle the communication buffer and improve sensing. The system is validated using advantage actor-critic (A2C) and proximal policy optimization (PPO). Furthermore, we compare our solution with the existing design and demonstrate its superior performance by computer simulations.

This paper introduces a quantum framework for addressing reinforcement learning (RL) tasks, grounded in the quantum principles and leveraging a fully quantum model of the classical Markov Decision Process (MDP). By employing quantum concepts and a quantum search algorithm, this work presents the implementation and optimization of the agent-environment interactions entirely within the quantum domain, eliminating reliance on classical computations. Key contributions include the quantum-based state transitions, return calculation, and trajectory search mechanism that utilize quantum principles to demonstrate the realization of RL processes through quantum phenomena. The implementation emphasizes the fundamental role of quantum superposition in enhancing computational efficiency for RL tasks. Experimental results demonstrate the capacity of a quantum model to achieve quantum advantage in RL, highlighting the potential of fully quantum implementations in decision-making tasks. This work not only underscores the applicability of quantum computing in machine learning but also contributes the field of quantum reinforcement learning (QRL) by offering a robust framework for understanding and exploiting quantum computing in RL systems.