Search Results (94)

Sustaining cooperation under severe social dilemmas is a fundamental challenge in complex systems. This paper proposes a two-layer coupled network model integrating three neutral subpopulations, combining an upper human layer (Fermi rule) and a lower agent layer (Bush–Mosteller reinforcement learning). The core scientific contribution is revealing that the three-subpopulation structure induces closed invasion cycles. This cross-subpopulation reciprocal suppression effectively halts the global expansion of defectors. Monte Carlo simulations demonstrate that under a severe dilemma $(b=1.8$), optimizing the coupling strength boosts the cooperation persistence probability ($P_{CC}$) by 91% and reduces defection persistence ($P_{DD}$) by 55%, stabilizing the global cooperation rate at approximately 50%. Furthermore, for $b>1.26$, this model consistently outperforms the canonical BM model. Practically, these findings provide a theoretical foundation and a quantitative reference for designing cooperative mechanisms in human–machine collaboration and public governance. Full article

Russian state-sponsored disinformation has been described in policy and the operational literature, but it is less often formalized in game-theoretic terms. Here, a two-layered formal model is developed showing how adversarial perturbation of a communication channel can collapse cross-group felt understanding—the third-order intentional state/belief structure, established empirically by Livingstone, in which one group believes its perspectives are recognized and accepted as valid by another. The Analytical Model is a static Bayesian signaling game with binary types and a noisy channel parameterized by perturbation rate π. The Analytical Model shows that when recognition benefits exceed signaling costs, there exists a perturbation threshold π* = 1 − c_R/(u_R · p) above which mutual misrecognition becomes the unique Perfect Bayesian Equilibrium outcome. The Computational Model embeds this logic in an agent-based simulation on a homophilic stochastic block model and scale-free networks with continuous recognition capacity. Four substantive findings emerge: the closed-form analytical threshold from the Analytical Model predicts the boundary of collapse in the dynamic networked simulation; high network homophily protects cooperative behavior below π* but provides no rescue above it; bridge seeding—the placement of recognition-capable agents at structurally central cross-group positions—is the most effective of three policy interventions tested, rescuing cooperation even above π*; and uniform adversarial volume is approximately as damaging as strategically targeted adversarial precision across both small dense and large scale-free topologies, qualifying the operational claim that targeted disinformation should strictly outperform volume-based approaches. The model is illustrated with the German Atomausstieg (nuclear phase-out) case, and implications for clinical psychology, public policy, and intergroup recognition under psychological warfare are discussed. Full article

With the increasing penetration of renewable energy generation (REG) in novel distribution systems, active distribution networks (ADNs) integrated with microgrids (MGs) play a crucial role in enhancing the flexibility of regulation resources and promoting the accommodation of REG. To meet the operational requirements for efficient collaboration between ADNs and MGs under different dispatch time scales, this paper proposes a collaborative optimal dispatch strategy for multi-microgrid active distribution systems based on a hybrid game and variable time scales. Firstly, a transaction operation framework is constructed for the distribution network operator (DNO) and a multi-microgrid alliance (MMA), considering the peer-to-peer (P2P) transaction mode. On this basis, a day-ahead hybrid game model with a two-layer structure is constructed, the upper layer is a master–slave game with the DNO as the leader and the MMA as the follower, while the lower layer is a cooperative game for MGs within the MMA. An asymmetric Nash bargaining strategy based on contribution degree in P2P transactions is introduced to ensure equitable benefit allocation among cooperative MGs. Secondly, an intra-day rolling optimization model for reactive power and voltage based on variable time scales is proposed, which enhances the system’s responsiveness to real-time source–load power fluctuations by dynamically adjusting the dispatch time scale. Finally, the alternating direction method of multipliers (ADMM), integrated with a strategy separation mechanism, is adopted to efficiently solve the hybrid game model involving numerous 0–1 variables. The case study results indicate that, under the proposed strategy, the MMA’s power purchase cost from the DNO and ESS operational cost are decreased by 9.7% and 11.6%, respectively, while the system’s average deviation rate of node voltage decreases by 0.82%. Therefore, the proposed collaborative dispatch strategy can not only effectively reduce the system’s operational cost and ensure voltage stability but also significantly promote the accommodation of REG. Full article

Urban healthcare systems are fundamentally constrained by the mismatch between static resource configurations and dynamically evolving patient demand. Under the tiered healthcare system, traditional static planning methods struggle to capture the complexity and randomness of patient flows. While recent reinforcement learning (RL) approaches enable adaptive decision-making, they suffer from dimensionality explosion and unstable convergence due to massive action spaces and delayed spatiotemporal credit assignment in city-scale environments. To address this gap, we propose Twin–Game: a digital twin-driven hierarchical reinforcement learning (HRL) framework that formulates adaptive healthcare resource optimization as a “Twin Game” between a simulation-based game environment (Strategic Sandbox) and a hierarchical decision policy. First, we construct the “first twin”—an offline digital twin that serves as the Strategic Sandbox parameterized with Wuhan’s observed facility, population, and transportation data, while patient arrivals and disease profiles are generated synthetically under documented assumptions because individual-level clinical flow data are not publicly available. This environment integrates a dynamic gravity model with a two-way referral mechanism to represent the nonlinear coupling between hospital attractiveness, crowding levels, and patient choice behaviors. Second, we build the “second twin”—an Option-based HRL policy. The Manager (Macro-level Strategic Layer) uses a Deep Q-Network (DQN) for discrete spatial attention allocation; the Worker (Micro-level Execution Layer) uses Proximal Policy Optimization (PPO) for continuous, fine-grained controls such as bed expansion ratios and personnel scheduling. The two twins interact in a closed-loop game, performing strategy search and game evolution under complex constraints to optimize allocation. Experimental results from the Wuhan case indicate that the Twin–Game framework outperforms static baselines and single-layer RL in reducing average travel times, enhancing resource utilization, and improving tiered diagnosis and treatment within the simulation setting. The results should be interpreted as simulation-based decision-support evidence rather than direct clinical validation. This study provides a data-driven, game-theoretic decision support tool for building resilient urban healthcare systems. Full article

The era of zero-sum competition calls for e-commerce platforms to shift focus toward micro-market resilience. Existing research has split into two traditions: diagnostic studies offer detailed analyses of market failure but lack systemic application, while engineering studies develop deployable tools yet suffer from opaque mechanisms and hidden risks. This paper proposes the Signal–Belief–Decision (SBD) framework to bridge this divide, with the Signal layer transforming private information into verifiable public knowledge, the Belief layer aggregating dispersed signals into shared consensus, and the Decision layer encoding enforceable rules for incentive compatibility. Using an extended signaling game, we diagnose six vulnerability dimensions (VD1–VD6) that destabilize markets. Agent-based modeling then allows us to distill four design principles (DP1–DP4) that inform governance configuration. The SBD framework provides a middle-range theoretical architecture that reorients platform governance from reactive tooling to proactive, consumer-centric design. Full article

The safe operation of power battery systems relies on the dynamic symmetric equilibrium of electrochemical distribution and thermal management states, whereas fault occurrence is often accompanied by symmetry breaking. To achieve accurate fault diagnosis and symmetry restoration, this study proposes a symmetrical closed-loop framework (DBP-KG-FBN) that integrates digital battery passport (DBP) text mining, knowledge graph (KG), and fuzzy Bayesian network (FBN). Power battery fault diagnosis is critical to new energy vehicle (NEV) safety; however, conventional methods face two key limitations: (1) they inadequately exploit multi-source heterogeneous textual data in DBPs; and (2) they fail to handle uncertainty in fault propagation. The methodology proceeds as follows. First, a BERT-BiLSTM-CRF model extracts fault-related entities and relations from unstructured DBP text, which are structured into a Neo4j-based knowledge graph. Second, via rule-based topological mapping, the KG topology is transformed into a Bayesian network through structurally symmetric transformation between the semantic and probabilistic layers, with cyclic dependencies resolved by introducing latent variables. Third, network parameters are determined by integrating fuzzy set theory with game theory-based weighting to quantify uncertainty and subjectivity in expert evaluations, thereby achieving symmetric utilization of subjective and objective information. This enables bidirectional symmetric reasoning for forward fault prediction and backward fault traceability. Experimental results demonstrate that while maintaining symmetric stability of the diagnostic knowledge topology, the proposed DBP-KG-FBN method achieves a diagnostic accuracy of 0.92 (Top-3). This symmetrical closed-loop framework significantly outperforms fault tree analysis (FTA) and event tree analysis (ETA) in diagnostic accuracy and reasoning efficiency. It transforms unstructured DBP data into computable knowledge for intelligent battery diagnosis. Future work will expand the corpus via transfer learning and optimize adaptive weighting algorithms for expert evaluations. Full article

Human–AI systems often involve repeated interaction among users, organizations, and AI components rather than isolated model outputs. In such settings, cooperation can be pursued either by changing agent incentives or by adding an explicit accountability layer. We formalize the Institutional Monitoring and Ledger (IML) framework, which augments a Markov game with monitoring, evidence logging, delayed settlement, and review while leaving the base dynamics unchanged. We derive conservative incentive checks that clarify how detection quality, review accuracy, settlement delay, and sanction size jointly shape deterrence and wrongful-penalty risk. We then provide pilot evidence in two canonical sequential social dilemmas, Harvest and Cleanup, using five agents, PPO training, five training seeds per condition, and comparisons against PPO, inequity aversion, social influence, and IML ablations. In these settings, IML avoided some of the optimization instability observed in the representative internalization baselines tested here, made monitoring error directly visible through ledger records, and showed how false positives can accumulate into a persistent welfare cost. Agent-level analyses in these symmetric environments found nearly uniform measured enforcement burden, while temporal analyses showed that late-stage enforcement is increasingly dominated by residual false positives. These results do not establish legitimacy in human-facing settings or deployment readiness. They instead position IML as a framework with pilot evidence for studying accountability mechanisms in cooperative human–AI systems and highlight measurement error, review design, and due process as central design constraints. Full article

As the core of digital infrastructure, the exceptionally rapid development of data centers (DCs) faces serious challenges due to their high electricity costs. Traditional approaches treat computational task scheduling separately from different physical control mechanisms, such as server group management, overlooking the synergistic potential between the two aspects. To address this problem, this paper proposes a computational–physical collaborative optimization model that realizes spatiotemporal task migration on the computational side and adaptive parameter regulation of IT equipment and cooling devices on the physical side. In response to the lack of global coordination in conventional distributed optimization, a two-layer partially observable Markov game (POMG) is constructed to unify global cooperative decision-making and local autonomous control. On this basis, the hierarchical multi-agent deep deterministic policy gradient (H-MADDPG) algorithm is designed by introducing task priority ranking and a variable-dimension action mask mechanism, which effectively handles the discrete–continuous hybrid action space and adapts to the dynamic variation in action dimensions caused by uncertain task arrivals. Comparative experiments with various benchmark schemes are conducted to verify the effectiveness and superiority of the proposed strategy in total cost, power usage effectiveness (PUE), resource utilization, and load balancing. Full article

With grid-connected microgrids connected to power distribution networks, a hierarchical coordination scheduling framework is developed to solve the benefit allocation problem among different entities. Firstly, a bi-level master–slave game model with the power distribution network as the leader and the microgrids as the followers is proposed. For the leader, a two-stage robust optimization economic dispatch model considering wind power uncertainty is established for the power distribution network. For the followers, an optimal-scheduling model considering time-of-use pricing and load demand response is constructed. Secondly, the follower model is transformed into the equilibrium constraints of the leader model in light of the Karush–Kuhn–Tucker condition. As a result, the above bi-level master–slave game model can be converted into a single-layer robust optimization problem with mixed-integer recourse, which is solved by the nested column-and-constraint generation algorithm. Finally, the proposed model and solution method are validated via an improved IEEE 33-bus distribution network connected with three microgrids. The simulation results demonstrate that the proposed model can reduce the total operation cost by 12.42% compared with the centralized optimization model. Moreover, the load demand response and the regulation of ESSs at the real-time scheduling stage can prominently improve the operation flexibility and reduce the operation cost. Specifically, the operation cost of multiple microgrids has reduced by 21.55% when considering load demand response. In addition, the solving time for the proposed model is 627.3 s, which has the potential for practical engineering application. Full article

The ramping requirement in new power systems primarily stems from net load variations and forecast errors of renewable energy and load. Designing an equitable cost allocation mechanism for ramping services based on these factors facilitates incentives for generation and load to actively reduce ramping demands, thereby alleviating system ramping pressure. Accordingly, this paper proposes a fair ramping cost allocation mechanism based on the ramping responsibility coefficients of market participants. Under this mechanism, a market-oriented operation model for wind–hydro-storage joint operation is established to verify its effectiveness in market applications. First, a ramping cost allocation mechanism is constructed based on ramping responsibility coefficients. According to the responsibility coefficients of market participants for deterministic and uncertain ramping requirements, ramping costs are allocated to the corresponding contributors in proportion to the ramping demands caused by net load variations, load forecast deviations, and renewable energy forecast deviations. Specifically, for costs arising from renewable energy forecast errors, an allocation mechanism is designed based on the difference between the declared error range and the actual error. Second, within this allocation framework, hydropower and storage (including cascade hydropower and hybrid pumped storage) are utilized as flexible resources to mitigate wind power uncertainty and reduce its ramping costs. A two-stage day-ahead and real-time bi-level game model for wind–hydro-storage cooperative decision-making is developed. The upper level optimizes bilateral trading and market bidding strategies for wind–hydro-storage, while the lower level simulates the market clearing process. Through Stackelberg game modeling, joint optimal operation of wind–hydro-storage is achieved, ensuring mutual benefits. Finally, simulation results validate that the proposed ramping cost allocation mechanism can guide renewable energy to improve output controllability through economic signals. Furthermore, the bilateral trading and coordinated market participation of wind–hydro-storage realize win–win outcomes, reduce the ramping cost allocation for wind power by 23.10%, effectively narrow peak-valley price differences, and enhance market operational efficiency. Full article

Scalable production of interactive 3D assets is a key requirement for XR-based applications, yet the functional integration of GenAI-generated assets into game engines remains challenging for non-expert users. This article proposes and validates a Prompt-to-Trigger workflow that links GenAI-based asset ideation and generation with the implementation of basic interactive behaviors (triggers) in accessible XR platforms. The study adopted a qualitative and exploratory approach, using systematic observation throughout a two-stage development process. This process included an initial phase where 3D assets were generated and refined using tools such as Tripo AI and Meshy, followed by an optimization stage to ensure compatibility with Blender and XR environments like A-Frame and Godot, and subsequently, the creation of AI-powered activation scripts. The results show that GenAI’s current 3D outputs frequently exhibit topological inconsistencies and rigging errors that compromise performance and real-time interoperability, requiring cleanup and optimization before deployment. The Prompt-to-Trigger workflow formalizes this bridge, positioning AI assistance as a functional layer for iterative logic generation. The resulting model provides non-expert creators with structured, actionable framework to prototype complex XR experiences for applied domains like education and multimedia communication. Full article

The performance of the pitcher is the cornerstone of baseball, often determining the flow and ultimate outcome of a game. Given this centrality, understanding the mechanics of an elite pitcher and decoding their strategies are paramount for both internal optimization and competitive scouting. This study proposes an end-to-end deep learning pipeline for automatically classifying five distinct pitch types from raw broadcast footage of MLB pitcher Max Scherzer between 2015 and 2020. By formulating pitch delivery as a time-series classification problem tailored to the unique biomechanics of an elite athlete, the proposed CNN–LSTM framework integrates per-frame spatial feature extraction using an advanced CNN backbone (YOLOv8s-cls) with a two-layer long short-term memory (LSTM) network to capture subtle biomechanical cues across a standardized 20-frame delivery sequence. While skeletal pose estimation primarily focuses on tracking major joints to analyze standard pitching mechanics, the proposed pixel-based method preserves fine-grained visual cues—such as finger grip and wrist rotation—that are critical for distinguishing pitch variations. The proposed framework achieved an accuracy of 91.8% under a standard Random Split and, importantly, 84.5% under a strict Chronological Split across different seasons, validating the feasibility of automated pitch “tell” detection from broadcast video. The resulting system provides coaches and analysts with an objective, data-driven tool for generating personalized scouting reports, identifying mechanical inconsistencies, and refining pitching strategies. Full article

Hydrogen energy storage serves as a pivotal technology for integrating high proportions of renewable energy, yet its development faces constraints due to substantial investment requirements and imperfect market mechanisms. Green Asset-Backed Notes (ABNs) offer potential to alleviate financing constraints; however, their synergistic effects with hydrogen storage market strategies remain unexplored. This paper constructs a two-layer Stackelberg game model integrating ABN financing with day-ahead trading. Multi-scenario analysis reveals that ABN financing costs significantly influence the operational economics of energy storage: low-cost financing enhances hydrogen storage’s price responsiveness and arbitrage capabilities, whereas high costs suppress its market participation. The research provides quantitative evidence for leveraging financial instruments to enhance hydrogen storage competitiveness. Full article

The development of the new energy vehicle (NEV) industry has become a key driver of the global low-carbon transition. Understanding the policy effect on NEV diffusion is essential to promote sustainable growth. In this study, we propose a new approach that combines a two-layer small-world network involving consumers and enterprises and evolutionary game theory to study the diffusion effect of industrial and trade policies on enterprises’ low-carbon production strategies and consumer preferences. Different from existing diffusion models, we integrate reinforcement learning (RL) into the decision-making process of enterprises and use SHapley Additive exPlanations (SHAP) to decode the micro-level decision logic of enterprises. In terms of the decision-making mechanism, the simulation results show that the Q-learning algorithm better fits the real market diffusion trend of NEVs compared with traditional algorithms; in terms of policy effects, industrial policies and trade policies exhibit a synergistic effect. SHAP analysis reveals that enterprises are more concerned about NEV market maturity than the impact of policy parameters on decision-making; Sobol sensitivity analysis indicates that consumer subsidies have a greater impact on the market diffusion of NEVs than trade policies. Full article

To address collaborative decision-making challenges in the pharmaceutical logistics supply chain amid public health emergencies, this study integrates disappointment aversion, delay effects, and pharmaceutical value attenuation, constructing a three-echelon system. It adopts a “differential game-system dynamics (SD)” two-layer dynamic research method for in-depth synergy. The differential game model focuses on multi-agent dynamic strategic interactions, deriving time-series equilibrium solutions for the optimal effort levels, transportation efficiency, and profits under four decision modes (decentralized, government subsidy, cost-sharing, centralized) to clarify the dynamic impact laws of the core parameters. Compensating for its limitations in complex environmental coupling and practical variable integration, the SD model incorporates the patient consumption rate, inventory fluctuations, weather disturbances and other real factors to build a dynamic feedback system. It not only verifies the practical adaptability of the differential game equilibrium solutions but also reveals the evolutionary laws of supply chain performance and the amplified inter-mode performance differences under multi-factor superposition. This study finds that centralized decision-making performs the best in terms of transportation efficiency peaking, profit stability, and attenuation control. Pharmaceutical stability and enterprise effort levels positively drive benefits, while disappointment aversion and excessive delays exert inhibitory effects. Government subsidies need to be paired with collaborative mechanisms to avoid policy dependence. Management implications suggest that enterprises should prioritize the collaborative centralized-decision-making mode, establish risk-sharing and benefit-sharing mechanisms, precisely regulate key variables, and implement gradient subsidies with exit mechanisms to enhance the supply chain’s dynamic adaptability and achieve the triple optimization of “efficiency–profit–stability”. Full article