reinforcement learning

Learning human visual attention on 3D surfaces through geometry-queried semantic priors

Hybrid digital twin and reinforcement framework for intelligent network slicing and dynamic resource allocation in 5G edge computing environments

In the world of rapidly evolving communication networks, network demand and traffic are increasing, which makes efficient network slicing and resource allocation techniques a requirement. The existing models for network slicing and resource allocation lack efficient algorithms, limited generalization, and practical imp...

Towards reliable LLM evaluators: Discovering and internalizing explicit scoring logic

Large language models (LLMs) have become effective evaluators across a wide range of tasks, but in rigorous contexts such as educational measurement, a model that can produce plausible scores is not yet a reliable rater. A central limitation of current LLM evaluators is that their scoring logic remains implicit and is...

Fast finite-time adaptive optimal algorithm for stochastic multiagent systems under deception attacks and time-varying output constraints

An adaptive optimal neural network algorithm with fast finite-time convergence is proposed for stochastic multiagent systems (SMASs) under deception attacks, time-varying asymmetric output constraints and dead zones. An additional attack signal corrupts the state information of nonlinear systems, resulting in the unava...

Offline and offline-to-online reinforcement learning for bus holding control

Abstract Bus bunching is a self-reinforcing phenomenon in which a delayed bus boards more passengers, incurs further delay, and is caught by its follower. Holding a bus at a stop to regulate headways is a widely studied corrective measure, yet most evaluations rely on a single shaped objective rather than independent p...

Edukasi Anti-Bullying melalui Program "Detektif Teman Baik" untuk Membangun Pertemanan Positif Siswa SDN 006 Sambutan

Peer conflict and bullying behavior, manifested in verbal mocking and physical aggression, present significant challenges in elementary education environments, including at SDN 006 Sambutan. This study aimed to examine the implementation and effectiveness of the "Detektif Teman Baik" anti-bullying education program in...

Automatic Generation of Deep Learning Models Based on Heterogeneous Pre-Trained Model Stitching

Findings support the feasibility of MPMS-AG for automatic generation of customized deep learning models from heterogeneous pre-trained model libraries within the evaluated setting.

The Role of Parents in Developing Phonological Awareness in 4–5-Year-Old Children: A Case Study at Cahaya Hati Kindergarten

Phonological awareness is a fundamental skill that supports early literacy development in young children. This study aimed to: (1) analyze the role of parents in developing children's phonological awareness at home; (2) identify the factors that support parents' involvement in fostering children's phonological awarenes...

Constraint-guided multi-agent deep reinforcement learning for multi-microgrid energy management with mobile electric vehicles

Quantum Cryptography and AI Integration: Quantum-Resistant Defenses for Future Communication Systems Against Emerging Cyber Threats

Quantum cryptography, like QKD, leverages quantum mechanics for unbreakable encryption against quantum computers, but faces deployment hurdles in key management, scalability, and noise. AI integration revolutionizes this by optimizing protocols, minimizing errors, and enabling real-time monitoring. Deep and reinforceme...

A Study of Myopic, Predictive, and Reinforcement Learning Energy Management Strategies for Isolated Microgrids

The increasing penetration of renewable energy sources in isolated microgrids has intensified the need for Energy Management Systems (EMS) capable of reducing diesel dependence while ensuring reliable operation. This study compares three EMS strategies for a photovoltaic–diesel–battery microgrid representative of remot...

Urban electric vehicle fast charging load forecasting: an LGRL approach

Test results show that the proposed hybrid forecasting method outperforms traditional algorithms in forecasting accuracy, convergence speed, and robustness under extreme conditions such as data missing, and it can effectively quantify the impact of load fluctuations on the voltage of distribution networks.