reinforcement learning

Artificial Intelligence Approaches for Insurance Claim Analytics in Synthetic Environments

Insurance claim analytics is often constrained by limited access to real-world data, which restricts the evaluation of advanced artificial intelligence approaches in practical insurance settings. Leveraging the SynthETIC framework, this study systematically evaluates classical actuarial models, neural-network-based met...

Device-physics design rules for wide-temperature enhancement-mode GaN integrated circuits: code and circuit-level results

Code and circuit-level results for the article "Device-physics design rules for wide-temperature enhancement-mode gallium nitride integrated circuits, revealed by transistor-anchored machine learning" (T. M. Mahim, M. M. Rahman, N. Chowdhury; submitted). The probe circuit is a monolithic e-mode GaN-on-SOI fractional-N...

Recent Advances in Cold-Sprayed Aluminum Alloy 7075 Metal Matrix Composite Coatings: Surface Engineering, Feedstock Design, Post-Processing Strategies, and Emerging Applications

Cold spray technology has emerged as a transformative solid-state processing route for fabricating high-performance metal matrix composite (MMC) coatings, particularly for lightweight, high-strength aluminum alloy 7075 (AA7075). This review provides a comprehensive overview of recent advances in cold-sprayed AA7075-bas...

Selective Memory and Adaptation in Nonstationary Reinforcement Learning

HyperFusionNet: An Intelligent DRL Framework with Neural Attention and Memory Integration for Optimized IoT Communication and Energy Efficiency

The sheer increase in IoT networks has created major challenges in the effective management of data communication, and high latency, limited power supply resources, and unreliable networks are some of the problems that have been encountered. All these limitations pose challenges to the scalability and performance of th...

Smart Education Platform: Based on Emotions Content Delivery Using ML

This project proposes a Smart Education Platform that dynamically adapts online learning content based on students’ real-time emotions to improve engagement and outcomes. Leveraging multimodal inputs—facial expressions detected via webcam using ResNet, speech sentiment analysis through Wav2Vec, and contextual surveys t...

Before you use it: Validating a tactical command vocabulary for multi-agent shooters

Multi-agent reinforcement learning evaluates communication by its effect on task reward, which cannot separate messages that were understood and acted on from messages that were ignored while the policy improved for other reasons. Separating them needs a verdict on the individual message, and that needs a discrete comm...

Human-Centered Digital Twins: A Bidirectional WebXR-Based Architecture for Immersive Interaction

Digital twin technology has emerged as a profound paradigm for bridging physical systems and their virtual counterparts through real-time data synchronization and interactive three-dimensional visualization. However, existing digital twin platforms are predominantly domain-specific, proprietary, and reliant on dedicate...

Source Code and Evaluation Data for Adaptive MPC Safety Shield in Microrobot Navigation

This repository contains the complete source code, configuration files, and raw evaluation data associated with the study on microrobot navigation. It includes the Python implementation of the Adaptive MPC Safety Shield integrated with DreamerV3 and TQC reinforcement learning algorithms. Additionally, it provides the s...

THE EL-RAKHAWI GRAND UNIFIED THEORY OF QUANTUM-BIO-COSMIC SYMBIOSIS AND PLANETARY HYPER-REGENERATION With the TQC-AI Framework as the Foundational Engine of Existential Harmony

The El-Rakhawi Grand Unified Theory of Quantum-Bio-Cosmic Symbiosis and Planetary Hyper-Regeneration (DOI: 10.5281/zenodo.23282366) proposes a unified, self-sustaining planetary operating system integrating five macro-pillars: a Quantum-Neural Core, Stellar-Terrestrial Energy Matrix, Bio-Exploration, Bio-Digital Interf...

ViST-MAPPO reproduction package: code, SUMO scenarios and per-seed results

Reproduction package for the manuscript Vision-Based Multi-Agent Reinforcement Learning for Traffic Signal Control: A Scale-Matched Simulation Study of State Representation and Message Passing. Contains SUMO 1.12.0 network, route and vehicle-type files, signal programs, training and evaluation code, per-seed results, a...

A Review of Energy-Efficient Routing Protocols for Underwater Acoustic Wireless Sensor Networks

Underwater acoustic sensor networks (UASNs) are key enabling technology for the Internet of Underwater Things (IoUT), supporting environmental monitoring, offshore exploration, disaster warning and surveillance. Existing routing approaches include depth- and hop-by-hop schemes, geographic/vector-based forwarding, clust...