reinforcement learning

Swin-Yoked neural architecture optimized by PaCFIQ for intelligent predictive security in WSN-IoT environments

Security in Wireless Sensor Network-based Internet of Things (WSN-IoT) systems is becoming increasingly important in the face of many cyber-attacks. This paper presents a smart framework, Swin-Yoked Neural Approach to Predictive Security (SYNAPSE) with a Parrot-CatchFish Integrated Q-Learning (PaCFIQ) optimizer to addr...

Revisiting multi-objective three-dimensional trajectory planning in dynamic unmanned aerial vehicles assisted systems using online Monte Carlo Search methods

Trajectory planning for Unmanned Aerial Vehicles (UAVs) in complex three-dimensional (3D) environments is a critical challenge in UAV-assisted task planning systems, particularly in dynamic scenarios such as rescue operations where UAVs serve as mobile wireless communication hubs. This paper addresses this challenge by...

Introduction

In this opening chapter, we set the stage for the book by describing both the opportunities and risks that artificial intelligence (AI) presents as it becomes increasingly embedded in critical domains such as healthcare, education, transportation, energy, conservation, and security. We argue that researchers and practi...

AI for Sustainable Energy Management

As renewable energy sources and electric vehicles proliferate, managing energy efficiently under uncertainty has become critical. This chapter focuses on optimization challenges in electric vehicle (EV) charging and vehicle-tobuilding (V2B) integration, formalizing them as sequential decision-making problems under unce...

Emergent problem-graph alignment in RL-discovered entanglement topologies for QAOA

In the Quantum Approximate Optimization Algorithm (QAOA), the entanglement topology, where qubit pairs are connected by two-qubit gates, is conventionally set equal to the edge set of the problem graph. This coupling ties circuit design to explicit problem knowledge and may not yield the most trainable circuit under li...

A Nonasymptotic Theory of Seminorm Lyapunov Stability: From Deterministic to Stochastic Iterative Algorithms

We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the nonasymptotic behavior of iterative algorithms in both deterministic and stochastic settings. In the deterministic setting, we present a fixed-point theorem for seminorm-contractive operato...

Hybrid deep reinforcement learning-assisted adaptive TID controller for sensorless BLDC motor drives with torque ripple minimization and dynamic stability enhancement

A reinforcement learning-guided breakout local search algorithm for the heaviest subgraph problem

TamRL - Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin - Artifact Data

This artifact contains result data and models for the paper Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin. Corresponding code can be found at https://github.com/MatCos/TamRL for the Reinforcement Learning Framework, and at https://github.com/niklasmedinger/Tamarin-ML-API...

Self-Configuring Hierarchies with Meta-Adaptive Hierarchical Reinforcement Learning for Multi-Agent cooperative Control

Solves the rigidity of manual hyperparameter tuning in traffic control using Meta-MOHRL, a self-configuring HRL framework for optimizing unpredictable multi-objective traffic flows. A PyTorch framework enabling multi-objective traffic coordination. Includes SUMO environment & topologies, and SoTA hierarchical baselines...

Camouflage-resistant graph neural networks for power grid anomaly detection

Abstract Power grid anomaly detection requires modeling both network topology and device dependencies. Graph neural networks (GNNs) are suitable for this task. However, few prior works have considered the stealthy camouflage behavior of grid anomalies, where faulty devices or malicious attackers intentionally mask thei...

An Intelligent Deep Reinforcement Learning Framework for Cost-Efficient and Energy-Aware Cloud Resource Management

The rapid growth of cloud computing and Internet of Things (IoT) applications has intensified the need for efficient resource allocation, energy management, and cost optimization in large-scale data centers. Traditional optimization and machine learning approaches, while effective in static environments, often fail to...