reinforcement learning

Decoupled multi-dimensional reinforcement learning with temporal communication for vision-based UAV control in partially observable environments

Modeling Patient Care Pathways as Markov Chains

Healthcare involves complex processes where patients move through multiple stages of care. Understanding these pathways is essential for improving outcomes. This chapter presents a pedagogical, worked-example application of Markov chain modeling to patient care pathways using the MIMIC-III Clinical Database Demo. The m...

Adaptive State of Charge and State of Health Estimation through Optimized Deep Reinforcement Learning with Dynamic Agent Selection and Test-Time Training Tailored to Dynamic Operating Conditions

Abstract Accurately estimating the state of charge (SOC) and state of health (SOH) of lithium−ion batteries under dynamic conditions is critical for electric vehicles (EVs) and energy storage systems; however, nonlinearity and uncertainties hinder traditional methods. This paper proposes an adaptive estimation framewor...

Adaptive Switching Between Self-Selection and Collaborative Selection in Multi-Agent Systems: A Unified Decision-Making Framework

Multi-agent systems must repeatedly select actions, solutions, resources, partners, strategies, or organizational configurations while operating under uncertainty and limited computational resources. Existing approaches often emphasize individual decision-making, collaborative decision-making, or predefined coordinatio...

Text to SPARQL via LLMs fine-tuned with rewards and reasoning

Large language models have made notable progress in translating natural-language questions into SPARQL queries for knowledge graphs. Recent studies from the first Text2SPARQL challenge have explored zero-shot and few-shot scenarios, as well as in-context learning techniques. With state-of-the-art (SoTA) results, the ch...

A Hybrid Graph Neural Network–Deep Reinforcement Learning Framework for Robust Multi-Modal Sensor Fusion and Real-Time Dynamic Obstacle Detection in Autonomous Environments

The research presents an intelligent framework for autonomous systems that performs multimodal sensor fusion to improve the identification of obstacles operating in dynamic scenarios.The proposed solution allows robots to handle complex and messy situations.The system leverages graph neural networks to capture spatial...

Mission-Horizon Hierarchical Reinforcement Learning for Fleet-Level PHM Under Resource-Constrained Operations

Fleet-level prognostics and health management (PHM) requires decisions that extend beyond diagnosis, remaining useful life estimation, and maintenance timing. Mission commitment, aircraft dispatch, maintenance, and spare-parts support consume the same finite sustainment capacity but operate at different temporal scales...

Evaluating the Effectiveness of an AI-Assisted Personalized Learning Pathway in Mobile-Supported Online Physical Education

This study evaluates the effectiveness of an AI-assisted personalized learning pathway in mobile-supported online physical education. To overcome issues of homogeneous content and delayed feedback, a system integrating cognitive knowledge, physical fitness, and motor skills was developed. Reinforcement learning dynamic...

A privacy-preserving task offloading method in collaborative mobile edge and cloud computing based on deep reinforcement learning

(منظومة المختبر الكيميائي الذكي المستقل المأهول بروبوتات شبيهة بالإنسان وأجهزة تفاعلية متعددة الوسائط).

الوصف التقني المموه والمطول للاختراع (Deeply Obfuscated & Extended Technical Description) 1. النطاق الأرشيتكتوري للكيانات الحسابية والتشغيلية الموزعة (Distributed Algorithmic Entity Fabric) تعتمد البنية الهيكلية للاختراع على مصفوفة متجانسة مؤلفة من عشر عقد تشغيلية ذاتية الموائمة الميكانيكية والهندسية، تتميز بتجريد تام...

Priority-driven reinforcement learning for safe control: addressing internal dependent state constraints in non-affine discrete-time systems

This work presents a model-free reinforcement learning methodology for output tracking control of unknown non-affine discrete-time systems with explicit safety guarantees on internal states. The proposed framework employs a fuzzy rule-emulated actor-critic architecture – built on two Multi-Input Fuzzy Rule-Emulated Net...

Behavioral Organization in Embodied AI: A Three-Level Survey

Recent years have witnessed a rapid proliferation of learning, control, and planning algorithms for embodied AI. However, grouping methods by model family or learning paradigm often separates approaches serving the same behavioral function, hindering comparison. To address this gap, this survey classifies robotic manip...