Search Results (402)

Pollination syndromes reflect the convergence of floral traits among plants sharing the same pollinator guild. However, bee-pollinated orchids exhibit striking variation in color and size. This diversity reflects the multiple reward strategies that evolved within the family, each interacting differently with bee sensory biases. Here, we tested whether the complex floral visual displays of orchids differ in signal identity and intensity among reward systems. We also considered intrafloral modularity, measured as the color differentiation among flower parts, and color–size integration. For this, we measured and modeled floral morphometric and reflectance data from sepals, petals, lip tips, and lip bases under bee vision from 95 tropical Epidendroid species to compare chromatic and achromatic contrasts, spectral purity, and mean reflectance across wavebands, plus flower and display size, among reward systems. Reward types included 19 food-deceptive, 8 nectar-offering, 10 oil-offering, 11 fragrance-offering, and 47 orchid species of unknown reward strategy. Principal component analyses on 34 color and 9 size variables summarized major gradients of visual trait variation: first component (19.1%) represented overall green-red reflectance and achromatic contrasts, whereas the second (16.5%) captured chromatic contrast–size covariation. Reward systems differed mostly in signal identity rather than signal intensity. Flower chromatic contrasts presented strong integration with flower size, while achromatic contrasts were negatively associated with display size. While deceptive and nectar-offering orchids tend toward larger solitary flowers with bluer and spectrally purer displays, oil- and fragrance-offering orchids tend toward smaller, brownish, or yellow to green flowers, with larger inflorescences. Rewardless orchids presented more achromatically conspicuous signals than rewarding orchids, but smaller displays. Orchid species clustered by reward both in PCA spaces and in bee hexagon color space. Deceptive orchids were typically associated with UV + White colors, oil orchids with UV + Yellow lip tips, and fragrance orchids with UV-Black lip bases and UV-Green lip tips. Together, these results indicate that orchid reward systems promote qualitative rather than quantitative differentiation in visual signals, integrating display color and size. These long-evolved distinct signals potentially enable foraging bees to discriminate among resource types within the community floral market. Our results demonstrate that color and flower display size are important predictors of reward strategy, likely used by foraging bees for phenotype-reward associations, thus mediating the evolution of floral signals. Full article

Conventional educational assessments enforce a rigid and symmetrical framework of identical question sequences upon a learner population inherently defined by asymmetry in cognitive capabilities and knowledge profiles. This mismatch results in inefficient measurement, where the uniform distribution of difficulty fails to mirror the heterogeneous nature of student learning. We address these topological and informational asymmetries through HARLA-ED, a hybrid framework combining deep knowledge modeling with intelligent question selection. The system integrates hierarchical cognitive graph networks to map the structural symmetries of concept dependencies while tracking evolving knowledge states across multiple time scales. By capturing both immediate working-memory constraints and long-term retention patterns, the model resolves the temporal asymmetry between learning and forgetting rates. A hierarchical reinforcement learning agent then orchestrates an assessment strategy through three decision levels: high-level planning determines diagnostic objectives, mid-level control sequences question types, and low-level actions select specific items. Crucially, the agent employs information-theoretic reward functions designed to restore distributional symmetry in assessment outcomes, ensuring demographic parity and minimizing algorithmic bias. Empirical results demonstrate a 47.5% average reduction in assessment duration compared to standard computer-adaptive tests while preserving measurement accuracy. The system successfully adapts to varying proficiency levels, effectively bridging the information asymmetry between the testing system and the learner’s true latent state. Full article

With the rapid growth of residential electric vehicles, synchronized charging during peak periods can induce severe load ramping and exceed distribution network capacity limits. To mitigate these issues, governments have promoted a unified build-and-operate community model that enables centralized coordination of community charging and ensures real-time responsiveness to grid dispatch signals. Targeting this emerging operational paradigm, a dual-dimensional compensation mechanism for real-time electric vehicle (EV) demand response is proposed. The mechanism integrates two types of compensation: power regulation compensation, which rewards users for providing controllable power flexibility, and state-of-charge (SoC) loss compensation, which offsets energy deficits resulting from demand response actions. This dual-layer design enhances user willingness and long-term engagement in community-level coordination. Based on the proposed mechanism, a bi-level optimization framework is developed to realize efficient real-time regulation: the upper level maximizes the active response capacity under budget constraints, while the lower level minimizes the aggregator’s total compensation cost subject to user response behavior. Simulation results demonstrate that, compared with conventional fair-share curtailment and single-compensation approaches, the proposed mechanism effectively increases active user participation and reduces incentive expenditures. The study highlights the mechanism’s potential for practical deployment in unified build-and-operate communities and discusses limitations and future research directions. Full article

Background/Objectives: Acute stress is known to influence food-related motivation and decision-making, often promoting a preference for energy-dense, palatable foods. However, traditional laboratory paradigms have limited ecological validity. This study examined the relationship between stress-induced physiological changes, eating behavior traits, and food cravings using a virtual reality (VR) adaptation of the Trier Social Stress Test (VR-TSST) followed by a VR supermarket task in adolescents. Methods: Thirty-eight adolescents (mean age 15.8 ± 0.6 years) participated in the study. Physiological parameters (HR, QT, PQ intervals) were recorded pre- and post-stress using a portable ECG device (WIWE). Perceived stress and eating behavior traits were evaluated with the Perceived Stress Scale (PSS) and the Three-Factor Eating Questionnaire (TFEQ-R21C), respectively. Immediately after the VR-TSST, participants performed a VR supermarket task in which they rated cravings for sweet, fatty, and healthy foods using visual analog scales (VAS). Paired-samples t-tests examined pre–post changes in physiological parameters, partial correlations explored associations between ECG responses and eating traits, and a 2 × 3 mixed-model Repeated Measures ANOVA assessed the effects of food type (sweet, fatty, healthy) and uncontrolled eating (UE) group (low vs. high) on post-stress cravings. Results: Acute stress induced significant increases in HR and QTc intervals (p < 0.01), confirming a robust physiological stress response. The ANOVA revealed a strong main effect of food type (F(1.93, 435.41) = 168.98, p < 0.001, η²p = 0.43), indicating that stress-induced cravings differed across food categories, with sweet foods rated highest. A significant food type × UE group interaction (F(1.93, 435.41) = 16.49, p < 0.001, η²p = 0.07) showed that adolescents with high UE exhibited greater cravings for sweet and fatty foods than those with low UE. Overall, craving levels did not differ significantly between groups. Conclusions: The findings demonstrate that acute stress selectively enhances cravings for high-reward foods, and that this effect is modulated by baseline uncontrolled eating tendencies. The combined use of VR-based stress induction and VR supermarket simulation offers an innovative, ecologically valid framework for studying stress-related eating behavior in adolescents, with potential implications for personalized nutrition and the prevention of stress-induced overeating. Full article

Objectives: This paper presents an innovative control framework for the classical Cart–Pole problem. Methods: The proposed framework combines Interval Type-2 Fuzzy Logic, the Dueling Double DQN deep reinforcement learning algorithm, and adaptive reward shaping techniques. Specifically, fuzzy logic acts as an a priori knowledge layer that incorporates measurement uncertainty in both angle and angular velocity, allowing the controller to generate adaptive actions dynamically. Simultaneously, the deep Q-network is responsible for learning the optimal policy. To ensure stability, the Double DQN mechanism successfully alleviates the overestimation bias commonly observed in value-based reinforcement learning. An accelerated convergence mechanism is achieved through a multi-component reward shaping function that prioritizes angle stability and survival. Results: Given the training results, the method stabilizes rapidly; it achieves a 100% success rate by episode 20 and maintains consistent high rewards (650–700) throughout training. While Standard DQN and other baselines take 100+ episodes to become reliable, our method converges in about 20 episodes (4–5 times faster). It is observed that in comparison with advanced baselines like C51 or PER, the proposed method is about 15–20% better in final performance. We also found that PPO and QR-DQN surprisingly struggle on this task, highlighting the need for stability mechanisms. Conclusions: The proposed approach provides a practical solution that balances exploration with safety through the integration of fuzzy logic and deep reinforcement learning. This rapid convergence is particularly important for real-world applications where data collection is expensive, achieving stable performance much faster than existing methods without requiring complex theoretical guarantees. Full article

Background/Objectives: Computational studies using drift diffusion models on go/no-go escape tasks consistently show that individuals with suicidal ideation (SI) preferentially engage in active escape from negative emotional states. This study extends these findings by examining how individuals with SI update beliefs about action–outcome contingencies and uncertainty when trying to escape an aversive state. Methods: Undergraduate students with (n = 58) and without (n = 62) a lifetime history of SI made active (go) or passive (no-go) choices in response to stimuli to escape or avoid an unpleasant state in a laboratory-based negative reinforcement task. A Hierarchical Gaussian Filter (HGF) was used to estimate trial-by-trial trajectories of contingency and volatility beliefs, along with their uncertainties, prediction errors (precision-weighted), and dynamic learning rates, as well as fixed parameters at the person level. Bayesian mixed-effects models were used to examine the relationship between trial number, SI history, trial type, and all two-way interactions on HGF parameters. Results: We did not find an effect of SI history, trial type, or their interactions on perceived volatility of reward contingencies. At the trial level, however, participants with a history of SI developed progressively stronger contingency beliefs while simultaneously perceiving the environment as increasingly stable compared to those without SI experiences. Despite this rigidity, they maintained higher uncertainty during escape trials. Participants with an SI history had higher dynamic learning rates during escape trials compared to those without SI experiences. Conclusions: Individuals with an SI history showed a combination of cognitive inflexibility and hyper-reactivity to prediction errors in escape-related contexts. This combination may help explain difficulties in adapting to changing environments and in regulating responses to stress, both of which are relevant for suicide risk. Full article

This paper proposes a scheduling approach for multi-type spacecraft operational tasks that can be interleaved, considering constrained space–ground telemetry, tracking, and command (TT&C) resources, as well as task splitting. A mixed-integer linear programming model is formulated to maximize the total task completion reward under service time-window constraints for splittable and unsplittable routine tasks, continuous tracking requirements, coupling relationships between routine and continuous tracking tasks, temporal logic dependencies, visibility constraints, and non-overlapping scheduling conditions. To improve solution efficiency and scheduling performance, a heuristic algorithm that combines priority rules with partial backtracking is developed. Task priorities are determined based on completion rewards, due times, execution durations, and temporal relationships, and scheduling is refined to avoid conflicts with predefined constraints. A partial backtracking mechanism guided by task release times enables effective adjustment when TT&C requirements cannot be satisfied. Comparative experiments with CPLEX and four heuristic algorithms validate the effectiveness of the proposed method. Full article

A condition-based maintenance decision-making framework for multi-component systems is proposed in this work by integrating dynamic Bayesian network (DBN) with proportional hazards model (PHM). The framework is designed to address the challenge of handling mixed failure types and complex failure dependencies, which often lead to inaccurate maintenance decisions in existing methods. In this integrated model, the DBN captures the failure evolution and both dynamic and static dependencies among components, while the PHM enhances the capability to characterize mixed failure interactions, thereby enabling the coverage of three common types of failure dependencies in multi-component systems. The model is formulated and solved using a finite-horizon Markov decision process (MDP), with the optimal maintenance strategy obtained by maximizing the total expected reward. Numerical case studies demonstrate the framework’s flexibility in handling mixed failures and complex dependencies, showing its potential to effectively support condition-based maintenance decision-making for complex multi-component systems. Full article

Unmanned Surface Vehicles (USVs) are increasingly employed in maritime operations requiring high levels of autonomy, safety, and energy efficiency. However, traditional path planning techniques struggle to simultaneously address multiple conflicting objectives such as fuel consumption, trajectory smoothness, and obstacle avoidance in dynamic maritime environments. To overcome these limitations, this paper introduces a Deep Q-Learning (DQN) framework and a novel Fuzzy Deep Q-Learning (F-DQN) algorithm that integrates Mamdani-type fuzzy reasoning into the reinforcement-learning (RL) reward model. The key contribution of the proposed approach lies in combining fuzzy inference with deep reinforcement learning (DRL) to achieve adaptive, interpretable, and multi-objective USV navigation—overcoming the fixed-weight reward limitations of existing DRL methods. The study develops a multi-objective reward formulation that jointly considers path deviation, curvature smoothness, and fuel consumption, and evaluates both algorithms in a simulation environment with varying obstacle densities. The results demonstrate that the proposed F-DQN model significantly improves trajectory optimality, convergence stability, and energy efficiency, achieving over 35% reduction in path length and approximately 70–80% lower fuel consumption compared with the baseline DQN, while maintaining comparable success rates. Overall, the findings highlight the effectiveness of fuzzy-augmented reinforcement learning in enabling efficient and interpretable autonomous maritime navigation. Full article

Background and Objectives: Anhedonia is a core symptom of major depressive disorder (MDD) and worsens its prognosis. Inflammation has been associated with MDD, contributing to the severity of this pathology despite no clear clinical guidance on whether it should be integrated into the diagnosis or treatment of the MDD symptomatology. Notably, the neural basis of anhedonia is associated with alterations in the reward neural circuit, where inflammation may also interfere. In this study, we investigate whether recent change in anhedonia was associated with low-grade inflammation (defined as C-Reactive Protein levels between 3 and 10 mg/L) in MDD subjects. Materials and Methods: A retrospective study was conducted on 496 MDD subjects and drawn from the database of the sleep laboratory. Recent change in anhedonia was assessed via the Anhedonia Subscale of the 21-items Beck Depression Inventory (BDI-II), with scores > 3 indicating its presence. Recent change in anhedonia was defined as the recent onset or worsening of anhedonia complaints within the past 2 weeks. Anxiety and sleep disturbances were also evaluated and inflammatory status was determined based on CRP levels. Results: After adjusting for the main confounding factors, the multivariate logistic regression confirms a clear association between recent change in anhedonia and low-grade inflammation, thereby contributing to a detrimental context underlying the symptom. Conclusions: A better understanding of anhedonia in the context of inflammation could enable treatment adjustments and improve the poor prognosis of anhedonia-type depression. Full article

Background: Glucagon-like peptide-1 receptor agonists (GLP-1RAs) have transformed treatment for higher weight and diabetes. Because they also influence appetite and reward processes, these medications may shape eating behaviours, emotions, and body image, raising new challenges for eating disorder (ED) research and clinical care. This narrative review synthesises emerging evidence on the psychological and behavioural effects of GLP-1RA use within a biopsychosocial and equity framework. Method: Using a narrative, non-systematic approach, we conducted targeted searches across major databases (2015–September 2025) with combined GLP-1RA and psychological or ED-related terms, supplemented by cross-referencing. Inclusion criteria focused on empirical, theoretical, and clinically meaningful psychological, behavioural, and sociocultural outcomes, enabling a conceptually driven synthesis of the psychological effects of GLP-1RA use. Results: GLP-1RAs reduce hunger and binge-eating frequency, suggesting possible benefits for binge-type EDs. However, evidence for restrictive EDs remains limited, and appetite suppression may reinforce rigid control or perfectionistic traits. Although short-term reductions in emotional eating have been reported, the long-term psychological safety of GLP-1RAs is unknown. Rapid, medication-driven weight loss may disrupt body perception, while social media discourse glamorises thinness and intensifies stigma. These psychosocial effects intersect with inequities in access, disproportionately affecting adolescents and individuals from culturally diverse or socioeconomically marginalised groups. Conclusions: GLP-1RAs sit at the intersection of medical innovation and psychological risk. To ensure safe and inclusive use, research and clinical practice should integrate developmental, cultural, and lived-experience perspectives. Co-designed research and multidisciplinary monitoring will be essential to reduce stigma, address inequities, and support psychologically informed care. Full article

Identifying effective coalitions of agents for task execution within large multiagent settings is a challenging endeavor. The problem is exacerbated by the presence of coalitional value uncertainty, which is due to uncertainty regarding the values of synergies among the different collaborating agent types. Intuitively, in such environments, a hypergraph can be used to concisely represent coalition–task pairs in the form of hyperedges, along with their associated rewards. Therefore, this paper proposes harnessing the power of Hypergraph Neural Networks (HGNNs) that fit generic hypergraph-structured historical representations of coalitional task executions to learn the unknown values of coalitional configurations undertaking the tasks. However, the fitted model by itself cannot be used to provide suggestions on which coalitions to form; it can only be queried for the values of given coalition–task configurations. To actually provide coalitional suggestions, this work relies on informed search approaches that incorporate the output of the HGNN as an indicator of the quality of the proposed coalition configurations. The resulting approach is illustrated, via simulation results, to be able to effectively capture the uncertain values of multiagent synergies and thus suggest highly rewarding coalitional configurations. Specifically, the proposed novel hybrid approach can outperform competing baseline approaches and achieve close to 80% performance of the theoretical maximum in this setting. Full article

The rapid growth of technology has introduced robots into daily life, necessitating navigation frameworks that enable safe, human-friendly movement while accounting for social aspects. Such methods must also scale to situations with multiple humans and robots moving simultaneously. Recent advances in Deep Reinforcement Learning (DRL) have enabled policies that incorporate these norms into navigation. This work presents a socially aware navigation framework for mobile robots operating in environments shared with humans and other robots. The approach, based on single-agent DRL, models all interaction types between the ego robot, humans, and other robots. Training uses a reward function balancing task completion, collision avoidance, and maintaining comfortable distances from humans. An attention mechanism enables the framework to extract knowledge about the relative importance of surrounding agents, guiding safer and more efficient navigation. Our approach is tested in both dynamic and static obstacle environments. To improve training efficiency and promote socially appropriate behaviors, Imitation Learning is employed. Comparative evaluations with state-of-the-art methods highlight the advantages of our approach, especially in enhancing safety by reducing collisions and preserving comfort distances. Results confirm the effectiveness of our learned policy and its ability to extract socially relevant knowledge in human–robot environments where social compliance is essential for deployment. Full article

Multi-agent inverse reinforcement learning (MA-IRL) infers the underlying reward functions or objectives of multiple agents by observing their behavioral data, thereby providing insights into collaboration, competition, or mixed interaction strategies among agents, and addressing the symmetrical ambiguity problem where multiple rewards may correspond to the same strategy. However, most existing algorithms mainly focus on solving cooperative and non-cooperative tasks among homogeneous multi-agent systems, making it difficult to adapt to the dynamic topologies and heterogeneous behavioral strategies of multi-agent systems in real-world applications. This makes it difficult for the algorithm to adapt to scenarios with locally sparse interactions and dynamic heterogeneity, such as autonomous driving, drone swarms, and robot clusters. To address this problem, this study proposes a dynamic heterogeneous multi-agent inverse reinforcement learning framework (GAMF-DHIRL) based on a graph attention mean field (GAMF) to infer the potential reward functions of agents. In GAMF-DHIRL, we introduce a graph attention mean field theory based on adversarial maximum entropy inverse reinforcement learning to dynamically model dependencies between agents and adaptively adjust the influence weights of neighboring nodes through attention mechanisms. Specifically, the GAMF module uses a dynamic adjacency matrix to capture the time-varying characteristics of the interactions among agents. Meanwhile, the typed mean-field approximation reduces computational complexity. Experiments demonstrate that the proposed method can efficiently recover reward functions of heterogeneous agents in collaborative tasks and adversarial environments, and it outperforms traditional MA-IRL methods. Full article

Binge eating disorder (BED) is a prevalent eating disorder lacking adequate pharmacological interventions. This review examines the therapeutic potential of glucagon-like peptide-1 receptor agonists (GLP-1RAs), medications approved for type 2 diabetes and obesity now being investigated for eating disorders through their modulation of metabolic and reward pathways. A narrative review was conducted using PubMed/MEDLINE, through May 2025, to examine GLP-1RA effects on BED, including preclinical and clinical studies, mechanistic investigations, and relevant reviews. GLP-1 receptors (GLP-1Rs) are expressed in hypothalamic nuclei, regulating energy homeostasis and mesolimbic circuits controlling food reward. Preclinical studies demonstrate that GLP-1RAs reduce food-seeking behavior, suppress dopamine signaling in reward circuits, and modulate neural transmission in key brain regions. These effects extend beyond appetite suppression to directly modify reward processing underlying compulsive eating. Emerging clinical evidence with semaglutide and liraglutide report reductions in binge eating episodes, decreased food cravings, and improved symptom scores. However, current studies remain small-scale with methodological limitations, and translating findings from animal models to human eating disorder complexity presents significant challenges. This review integrates preclinical and clinical evidence demonstrating that GLP-1RAs modulate both metabolic and reward pathways. By elucidating the underlying neurobiological mechanisms, GLP-1RAs may offer advantages over current symptom-focused therapies for BED. Full article