Search Results (110)

A collision-free path is not sufficient for visibility-dependent mobile robot tasks: a moving obstacle can block the camera–target line of sight and cause inspection or visual-servoing failure even when the robot remains physically safe. Maintaining visual contact with targets is therefore important in Industry 4.0 environments, yet visibility-preserving maneuvers can conflict with navigation progress and collision avoidance. This work presents the Visibility-Informed Safety and Target Awareness framework with control barrier function filtering and occlusion-evasive local replanning (VISTA-CBF+ELR). The architecture combines visibility-risk planning, target-bearing control, an ELR supervisor, and a CBF quadratic program that keeps collision constraints hard while relaxing field-of-view and occlusion requirements through slack. Counterproductive interventions are limited through persistence, benefit–cost and feasibility gates, progress protection, bounded dwell, recovery, and cooldown. In locked factory simulations, redesigned VISTA achieved 67% and 73% strict-goal success under clean and nominal sensing, whereas Visibility-CEM-2D achieved 87% and 86% but with lower clearance. In matched Gazebo trials, strict success was 19/30 for redesigned VISTA, 26/30 without ELR, and 16/30 for Nav2 Smac+MPPI; zero-clearance collisions were 8/30, 3/30, and 14/30, with no difference surviving multiplicity correction. A separate CEM stress test sustained 6.875 Hz optimization, missed 26.31% of 100 ms deadlines, and held commands on 31.35% of ticks. The results demonstrate repair of the ELR pathology and conditional visibility-risk reduction while exposing safety–visibility trade-offs, transfer limitations, and real-time constraints. Full article

Hyperparameter optimization (HPO) aims to identify high-quality model configurations under a limited evaluation budget. To address mixed search spaces, sparse feedback, and low sample efficiency in reinforcement learning (RL)-based HPO, a Center-Guided Reinforcement Learning (CGRL) method is proposed. In CGRL, the policy output is reformulated from a configuration to be directly evaluated into a search center that defines a promising region, decoupling region-level guidance from exact configuration selection. A mixed candidate pool is generated around the center, and a promising candidate for real evaluation is selected by a Random Forest surrogate model. Meanwhile, a process-aware reward provides dense and informative feedback for policy learning. Experiments on 20 Yet Another Hyperparameter Optimization (YAHPO) Gym environments validate the effectiveness of CGRL. Compared with random search (RS), Tree-structured Parzen Estimator (TPE), Sequential Model-based Algorithm Configuration 3 (SMAC3), a Proximal Policy Optimization baseline (PPO-basic), Hyperparameter Optimization by Reinforcement Learning (Hyp-RL), and Q-Learning for Hyperparameter Optimization (HyperQ-Opt), CGRL achieves the best average rank of 1.800 in terms of the final best objective value, versus 6.000, 3.600, 2.200, 4.450, 6.350, and 3.600, respectively. For Low-Rank Adaptation (LoRA) HPO for relation extraction (RE) from ancient Chinese historical documents, CGRL improves Macro-F1 by 8.66%, 3.10%, 3.18%, and 5.13% on the validation set relative to RS, TPE, SMAC3, and PPO, respectively, and by 11.15%, 2.03%, 3.11%, and 9.59% on the test set. These results demonstrate the effectiveness of CGRL for limited-budget HPO and its applicability to practical RE tasks. Full article

Diagnosis coding is a large-scale multi-label task in which each clinical encounter may require one or more coding labels from a large label space. Conventional top-k and threshold-based classifiers provide practical coding suggestions but do not directly characterize uncertainty over alternative coding sets. This study proposes sparse Mahalanobis conformal scoring for set prediction in diagnosis coding under extreme multi-label classification (XMC), intended for coding-assist workflows that require compact and reviewable coding suggestions. A sparse XMC model first generates candidate coding labels for each encounter. Candidate label sets are then constructed from the sparse proposal space and scored using a diagonal Mahalanobis nonconformity function calibrated on held-out data. Empirical conformal p-values are assigned to candidate sets, and downstream decision rules are used to obtain a final coding output from the retained region. The framework was evaluated using outpatient EHR data from a tertiary-care hospital, comprising approximately 8.0 million visits from 2018 to 2025 and up to 12,829 diagnosis labels. The primary SMaCS output achieved Micro-F1 close to the strongest threshold-based comparator and the highest exact match ratio among flexible-size decision rules. Compared with the other nonconformity scores, the Mahalanobis score produced a smaller retained region with fewer distinct labels, while preserving the same point-prediction performance. Additional analyses examined conformal region validity, robustness to label-frequency thresholds, code-depth performance, label-frequency subgroups, sample cardinality, department-level variation, and confidence–credibility stratification. Our results suggest that sparse Mahalanobis conformal scoring provides a useful framework for uncertainty-informed outpatient coding set prediction, while also highlighting the importance of candidate-space adequacy in extreme multi-label diagnosis coding. Full article

This work reports, for the first time, the use of agave bagasse from “Tequila Weber Var” as an efficient and eco-friendly template for the microwave-assisted solvothermal synthesis of C@TiO₂ photoelectrodes. The characterization of the C@TiO₂ materials was performed using composition and elemental analysis, diffuse reflectance/UV-visible spectroscopy, N₂ adsorption/desorption isotherms, scanning and transmission electron microscopy, energy-dispersive X-ray spectroscopy, X-ray diffraction patterns, cyclic voltammetry, impedance spectroscopy, and variations of the open-circuit potential in a conventional electrochemical cell. Three 1:1, 4:1, and 8:1 agave:Ti volume ratios were used to explore the influence of carbon content upon the optical and photoelectric properties of TiO₂. The composite with a 1:1 ratio showed a charge transfer kinetic capacity of 0.86 C·cm⁻²·s⁻¹ with the highest current density flow of 2.2 mA·cm⁻², and the lowest optical band gap (E_bg) value of 2.92 eV, boosting the optoelectronic behavior of TiO₂. The photoanode composed of FTO/C@TiO₂ with the hybrid material with a 1:1 ratio was preliminarily evaluated in a photovoltaic solar cell, showing a light-to-electricity conversion efficiency higher than the other two composites and up to 12.5 times higher than the photoanode only composed of neat TiO₂. The present results contribute to the state-of-the-art of eco-friendly organic–inorganic thin film photoelectrodes for the sustainable synthesis of third-generation solar cells using bagasse-derived waste as an efficient carbon source for the synthesis of hybrid photoactive semiconductors. Full article

Efficient coordination under limited communication is a central challenge in multi-agent reinforcement learning (MARL). Existing approaches often focus on message exchange without explicitly modeling how communication affects policy learning, leading to redundant interactions and limited coordination gains. In this paper, we propose a threshold-gated sparse communication framework built upon QMIX, a monotonic value-decomposition method that mixes individual agent action values into a global team action value. In the proposed framework, communication is integrated into the agent utility function to directly influence policy learning. Each agent encodes local observations into structured representations and activates communication through a learned trigger mechanism. Messages are aggregated via neighbor-constrained attention and incorporated into utility estimation for decentralized decision-making. Experimental results on the StarCraft Multi-Agent Challenge (SMAC) benchmark show that the proposed method improves coordination quality and training stability while significantly reducing communication frequency. On MMM, the Marine–Marauder–Medivac heterogeneous scenario, the communication rate is reduced to approximately 30–38% while achieving up to 96.6% win rate, compared to 92.1% for QMIX. On 10m_vs_11m, a homogeneous scenario where ten allied Marines fight against eleven enemy Marines, communication remains within 28–37% while reaching 88.4% win rate, compared to 85.6% for QMIX. Moreover, on the same task, varying communication thresholds induce clearly differentiated policy behaviors, indicating that sparse communication not only reduces overhead but also plays a critical role in shaping coordination policies. These results demonstrate that selective communication enables efficient coordination while explicitly regulating policy formation. Full article

Antiretroviral therapy (ART) effectively suppresses HIV-1 replication but does not purge the latent HIV-1 reservoir. Strategies aimed at HIV-1 latency reversal and subsequent elimination of infected cells are being explored. Targeting the inhibitor of apoptosis proteins (IAP) and DEAD-box polypeptide 3 (DDX3) RNA helicase reduces the HIV-1 reservoir ex vivo. However, the mechanisms driving apoptosis of HIV-1 infected cells remain unclear. Here, we uncovered the mechanism regarding HIV-1 transcriptional activation and induction of apoptosis specific for HIV-1 infected cells using an acute in vitro infection model. Inhibition of IAP by second mitochondrial-derived activator of caspases mimetic (SMACm; AZD5582) resulted in activation of non-canonical NF-κB pathway (RelB/p52) that induced HIV-1 transcription, confirming previous reports, whereas inhibition of DDX3 sensitized HIV-1 infected cells for apoptosis (DDX3i; FH1321). Transcriptome analysis revealed that HIV-1 actively suppressed apoptosis-related genes in HIV-1 infected cells. SMACm treatment resulted in a broad induction of these genes irrespective of infection. Notably, DDX3 inhibition specifically restored the expression of the majority of HIV-1 suppressed genes, and when combined with SMACm, restored almost all HIV-1 downregulated genes, thereby rendering HIV-1 infected cells sensitive to apoptosis. Thus, our data strongly suggest that inhibition of host factors IAP and DDX3 not only induces activation of HIV-1 transcription but also restores HIV-1 suppressed apoptotic processes in infected cells. Full article

Multi-Agent Reinforcement Learning (MARL) faces key challenges in credit assignment and the curse of dimensionality as agent numbers grow. In cooperative settings, uniform treatment of agents often exacerbates these issues. We argue that an agent’s importance depends on its personalized attributes and environment states and propose concentrating computational resources on key agents while others act simply, alleviating dimensionality explosion and improving generalization. We propose the Decision of Nonsynchronous Framework (DNF), which identifies and prioritizes key agents at each time step for optimized decision-making, while assigning predefined or simplified behaviors to the remaining agents based on computational outcomes. To realize this, we introduce a Core Extractor (CE) architecture that categorizes agents into Priorities Key Agents (PKAs) and followers. Although agents are differentiated by priority, we still adhere to the Centralized Training with Decentralized Execution (CTDE) paradigm. This approach reduces the dimensionality of the joint state-action space, mitigates the dimensionality explosion problem in MARL, and fosters improved collaboration among agents. Experimental results demonstrate that DNF achieves a 100% win rate on multiple SMAC maps, including 3m, 2s3z, and 1c3s5z, and achieves 98.9–100% win rates on challenging hard and super-hard scenarios such as 2c_vs_64zg and Corridor, significantly outperforming baseline methods like QMIX and QPLEX in both final performance and training stability, while incurring only a modest increase in computational overhead. In the continuous MPE, DNF matches or exceeds HAPPO in performance and demonstrates substantially higher time efficiency, with both advantages growing more pronounced as the number of agents increases. Full article

Bayesian optimization (BO) is a widely used framework for optimizing expensive black-box functions. Most BO methods rely on Gaussian process (GP) surrogates, which perform well in continuous domains but encounter difficulties when decision variables include categorical or mixed discrete–continuous components. In particular, GP-based approaches typically require ad hoc numerical encodings of categorical variables that may fail to capture the structure of discrete decision spaces. In this work, we propose MNL-BO (Multinomial Logit Bayesian Optimization), a preference-based Bayesian optimization framework that replaces the GP surrogate with a multinomial logit (MNL) model trained from pairwise preference comparisons. The resulting surrogate provides a natural and interpretable representation of categorical alternatives while allowing continuous, discrete, and categorical variables to be handled within a unified optimization framework. The predictive utility estimates and uncertainty indicators generated by the MNL model are employed to formulate acquisition functions that reconcile exploration with exploitation. The proposed methodology is evaluated on three progressively complex optimization challenges: a purely categorical benchmark, a combinatorial Traveling Salesman problem, and a constrained mixed-variable engineering design problem concerning material selection in pressure vessel optimization. Multi-run tests provide consistent advantages over random search and exhibit stable convergence behavior across diverse random initializations. In addition to heuristic baselines such as local search and classical metaheuristics, we also compare against tree-based Bayesian optimization baselines inspired by the Sequential Model-based Algorithm Configuration (SMAC) framework. The results indicate that the proposed MNL-BO method achieves competitive performance under comparable evaluation budgets while providing an interpretable probabilistic surrogate for categorical decision spaces. These findings suggest that preference-based surrogate modeling provides a practical and flexible alternative for Bayesian optimization in categorical and mixed-variable optimization problems. Full article

This paper presents an open-source ROS 2 navigation and sensor platform for quadruped robots, demonstrated on Boston Dynamics Spot in a laboratory environment. The platform integrates SLAM Toolbox for mapping and localisation, Navigation2 with MPPI and Smac Hybrid-A* for global path planning, and a frontier-based autonomous exploration module with practical handling of unreachable frontiers. The paper validates and verifies current, open-source algorithms deployed on off-the-shelf hardware. A greedy wavefront-based frontier selection method is presented that prioritizes Time-to-Closest-Viable-Frontier (TCVF) by terminating the search as soon as a feasible frontier is identified. On a real robot dataset replayed across five goal scenarios, the method reduces median selection latency from $94.31$ ms to $51.08$ ms (95th percentile: $109.54$ ms to $56.99$ ms), corresponding to a $1.85$-times improvement in compute time compared to a standard implementation. The system also employs Zenoh middleware and Foxglove for remote monitoring and control, enabling flexible, high-bandwidth operation. The platform, including configuration files and launch scripts, is released openly to support future research and deployment on quadruped robots. Full article

Background: Sirtuin 3 (SIRT3), a mitochondrial NAD⁺-dependent deacetylase, plays a central role in regulating mitochondrial metabolism, oxidative stress, and cell survival. Although SIRT3 has been implicated in angiogenesis, apoptosis, and inflammation, its global proteomic impact on the brain remains unclear. This study aimed to systematically characterize alterations in angiogenesis-, apoptosis-, chemokine-, and cytokine-related proteins in the brains of SIRT3 knockout (SIRT3 KO aka SIRT3⁻/⁻) mice compared with wild-type (WT) controls. Methods: Adult male C57BL/6 WT and SIRT3 KO mice were analyzed using proteome profiler antibody microarrays covering 53 angiogenesis factors, 21 apoptosis markers, 28 chemokines, and 111 cytokines. Protein expression changes were quantified by chemiluminescence imaging and densitometric analysis. Results: The results showed a distinct suppression of angiogenic proteins (amphiregulin, angiogenin, DPPIV, GM-CSF, IGFBP-2, IGFBP-3, IL-1β, PDGF-AA, PDGF-BB, proliferin, serpin F1, thrombospeondin-2, TIMP-4, and VEGF-B), activation of both pro-apoptotic (BAD, cytochrome c, Smac/DIABLO, HIF-1α, Fas, TNF R1, and TRAILR2) and anti-apoptotic, stress-related proteins (Bcl-x, catalase, HO/HMOX2, HSP27, HSP70, and MCL1) in the SIRT3 KO animals compared with the WT controls. Notably, SIRT3 deficiency was associated with increased expression of inflammatory mediators linked to glial activation and neurodegeneration (BLC/CCL13, LIX/CXCL5, MIG/CXCL9, chitinase 3-like 1, CCL22/MDC, IL-6, myeloperoxidase, osteopontin, RBP4, Reg3G, and TNF-α), alongside disturbed proteins involved in immune surveillance and vascular remodeling (6Ckine/CCL21, chemerin, DF, EGF, fractalkine/CX3CL1, HGF, IGFBP-6, IL-16, and I-TAC). Conclusions: Collectively, these findings demonstrate that SIRT3 is a key regulator of mitochondrial-dependent vascular, apoptotic, and neuroimmune pathways in the brain, and that its loss creates a molecular environment consistent with heightened vulnerability to neurodegenerative processes. Full article

MASH is a progressive liver disease closely associated with cellular senescence, which is present in more than 80% of hepatocytes in patients who develop hepatocellular carcinoma (HCC). Although MASH affects both sexes, the incidence of MASH-related HCC is two to four times higher in males. Our group has previously described two apoptotic switches during MASH progression and HCC development, implicating the ATP1A1 signalosome in the late switch. Here, we investigated the role of ATP1A1 and sex-specific differences in the early apoptotic switch during preclinical MASH progression. Male and female C57BL/6J mice (7 weeks old) were fed normal mouse chow (NMC) or a high-fat diet (HFD) for 12, 24, or 48 weeks (n = 5/sex/group). Total body weight (TBW) and body composition were assessed by serial measurement and echo-MRI. Plasma was analyzed by non-targeted metabolomics and glutathione profiling using LC-MS/MS. NAFLD activity scores (NAS), hepatic senescence, and apoptosis were quantified in liver tissue. Statistical analyses were performed using GraphPad Prism and R. Males gained greater TBW and lean and fat mass than females (p < 0.05). At 24 W, males demonstrated higher GSH:GSSG ratios and lower ophthalmate levels than females (p < 0.05), consistent with altered redox balance. HFD-fed females showed increased succinic and deoxycholic acid levels, whereas males exhibited higher butyric acid levels across all time points (p < 0.05). Males had a higher mTOR 1 expression at 24 W and P53 at 12 W compared to females on HFD, but a lower Grb2 expression at 24 W (p < 0.05). By 24 W, males had lower fibrosis scores and reduced apoptotic activity compared with females (p < 0.05), despite similar levels of cellular senescence. The expression of ATP1A1, survivin, and SMAC did not differ by sex or diet, although an upregulation trend in both ATP1A1 and survivin was noted in the male-HFD group. There is sexual dimorphism in the response to HFD during the transition from senescence to the apoptosis-first apoptotic switch in MASH progression. Full article

Value factorization methods have become a standard tool for cooperative multi-agent reinforcement learning (MARL) in the centralized-training, decentralized-execution (CTDE) setting. QMIX (a monotonic mixing network for value factorization), in particular, constrains the joint action–value function to be a monotonic mixing of per-agent utilities, which guarantees consistency with individual greedy policies but can severely limit expressiveness on tasks with non-monotonic agent interactions. This work revisits this design choice and proposes Relaxed Monotonic QMIX (R-QMIX), a simple regularized variant of QMIX that encourages but does not strictly enforce the monotonicity constraint. R-QMIX removes the sign constraints on the mixing network weights and introduces a differentiable penalty on negative partial derivatives of the joint value with respect to each agent’s utility. This preserves the computational benefits of value factorization while allowing the joint value to deviate from strict monotonicity when beneficial. R-QMIX is implemented in a standard PyMARL (an open-source MARL codebase) and evaluated on the StarCraft Multi-Agent Challenge (SMAC). On a simple map (3m), R-QMIX matches the asymptotic performance of QMIX while learning substantially faster. On more challenging maps (MMM2, 6h vs. 8z, and 27m vs. 30m), R-QMIX significantly improves both sample efficiency and final win rate (WR), for example increasing the final-quarter mean win rate from $42.3\%$ to $97.1\%$ on MMM2, from $0.0\%$ to $57.5\%$ on 6h vs. 8z, and from $58.0\%$ to $96.6\%$ on 27m vs. 30m. These results suggest that soft monotonicity regularization is a practical way to bridge the gap between strictly monotonic value factorization and fully unconstrained joint value functions. A further comparison against QTRAN (Q-value transformation), a more expressive value factorization method, shows that R-QMIX achieves higher and more reliably convergent win rates on the challenging SMAC maps considered. Full article

This paper presents the Multi-agent Transfer Learning Based on Contrastive Role Relationship Representation (MCRR), focusing on the unique function of role mechanisms in cross-task knowledge transfer. The framework employs contrastive learning-driven role representation modeling to capture the differences and commonalities of agent behavior patterns among multiple tasks. We generate generalizable role representations and embed them into transfer policy networks, enabling agents to efficiently share role assignment knowledge during source task training and achieve policy transfer through precise role adaptation in unseen tasks. Unlike traditional methods relying on the generalization ability of neural networks, MCRR breaks through the coordination bottleneck in multi-agent systems for dynamic team collaboration by explicitly modeling role dynamics among tasks and constructing a cross-task role contrast model. In the SMAC benchmark task series, including mixed formations and quantity variations, MCRR significantly improves win rates in both source and unseen tasks. By outperforming mainstream baselines like MATTAR and UPDeT, MCRR validates the effectiveness of roles as a bridge for knowledge transfer. Full article

This study presents the first quantitative meta-analysis in cooperative multi-agent reinforcement learning (MARL). Undertaken on the StarCraft Multi-Agent Challenge (SMAC) benchmark, we quantify reproducibility and statistical heterogeneity across studies using the five algorithms introduced in the original SMAC paper (IQL, VDN, QMIX, COMA, QTRAN) on five widely used maps at a fixed 2M-step budget. The analysis pools win rates via multilevel mixed-effects meta-regression with cluster-robust variance and reports Algorithm × Map cell-specific heterogeneity and 95% prediction intervals. Results show that heterogeneity is pervasive: 17/25 cells exhibit high heterogeneity (I² ≥ 80%), indicating between-study variance dominates sampling error. Moderator analyses find publication year significantly explains part of residual variance, consistent with secular drift in tooling and defaults. Prediction intervals are broad across most cells, implying a new study can legitimately exhibit substantially lower or higher performance than pooled means. The study underscores the need for standardized reporting (SC2 versioning, evaluation episode counts, hyperparameters), preregistered map panels, open code/configurations, and machine-readable curves to enable robust, heterogeneity-aware synthesis and more reproducible SMAC benchmarking. Full article

Cooperative Multi-Agent Reinforcement Learning (MARL) relies on effective coordination among agents to maximize team performance in complex environments. However, existing coordination graph-based approaches often overlook dynamic group structures and struggle to accurately capture fine-grained inter-agent dependencies. In this paper, we introduce a novel method called the Group Attention Aware Coordination Graph (G2ACG), which builds upon the group modeling capabilities of the Group-Aware Coordination Graph (GACG). G2ACG incorporates a dynamic attention mechanism to dynamically compute edge weights in the coordination graph, enabling a more flexible and fine-grained representation of agent interactions. These learned edge weights guide a Graph Attention Network (GAT) to perform message passing and representation learning, and the resulting features are integrated into a global policy via QMIX for cooperative decision-making. Experimental results on the StarCraft II Multi-Agent Challenge (SMAC) benchmark show that G2ACG consistently outperforms strong baselines, including QMIX, DICG, and GACG, across various scenarios with diverse agent types and population sizes. Ablation studies further confirm the effectiveness of the proposed attention mechanism, demonstrating that both the number of attention heads and the number of GAT layers significantly affect performance, with a two-layer GAT and multi-head attention configuration yielding the best results. Full article