reinforcement learning

RL-Based Adaptive Cyber Defence System

In the current connected digital world, cyber defence can no longer function in the traditional and signature-based protection, but it should adopt machine-speed adaptivity and intelligence. The ruthless development of threats, which involves zero-day exploits and polymorphic malware, among others, makes the convention...

Adaptive Traffic Signal Control at a Single Intersection Using Deep Reinforcement Learning: A SUMO-Based Comparative Study

Urban road networks lose a large amount of time and fuel to congestion at signalised intersections, and conventional fixed-time controllers cannot react to the changing and uneven traffic demand seen in practice. Reinforcement learning (RL), and in particular deep reinforcement learning (DRL), has been proposed as a wa...

Adaptive Traffic Signal Control at a Single Intersection Using Deep Reinforcement Learning: A SUMO-Based Comparative Study

Urban road networks lose a large amount of time and fuel to congestion at signalised intersections, and conventional fixed-time controllers cannot react to the changing and uneven traffic demand seen in practice. Reinforcement learning (RL), and in particular deep reinforcement learning (DRL), has been proposed as a wa...

An artificial intelligence-based two-stage framework for dynamic pricing and demand-side management in smart grids

Rapid urbanization, the rapid growth of electricity demand, and the widespread adoption of electric vehicles have increased the complexity of managing modern power systems. Conventional fixed pricing mechanisms are increasingly insufficient to ensure efficient energy utilization, peak load mitigation, and system resili...

Auditing Single-Agent Reinforcement Learning for EV Charging Assignment: A Protocol-Amended Comparison of Trained, Untrained, and Heuristic Policies

Deep reinforcement learning (DRL) is widely assumed to outperform simpler rule-based and tabular baselines for sequential decision problems. We test this assumption for electric vehicle (EV) charging assignment using Simulation of Urban MObility (SUMO) simulations of real Rabat and Tangier road networks, with a protoco...

AI-Driven Data Governance Framework for Enterprises in Cloud Environments: Design, Implementation, and Enterprise Evaluation

Challenges cloud-based enterprise data governance is encountering include data growth, regulatory changes, and the inflexibility of traditional rule-based systems. This systematic literature review, based on PRISMA guidelines, analyses 67 peer-reviewed papers (2019–2026) under three research questions related to AI-dri...

Arcstone Executive Epistemic & Execution Series: Human-First Trust, Machine-First Execution, Hybrid Alignment, Machine-Native Authority, Admissibility Science, Isomorphic Architecture, and Literature Synthesis (EXEC01–EXEC04, CORE01–CORE02, META01, LIT003)

===============================================================================ARCSTONE EXECUTIVE EPISTEMIC & EXECUTION SERIES (EXEC01–EXEC04, CORE01–CORE02, META01, LIT003)Primary Suite DOI Anchor: 10.5281/zenodo.22665852Master System Hash Anchor: A-77-DELTA-SHIELD-LOCKEDCanonical Handle: @admissibilityscience========...

AI-Driven Microarchitectural Optimization and Automated Datapath Synthesis in Modern Computer Architecture

Artificial Intelligence (AI) can support modern computer architecture by automating the exploration and optimization of microarchitectures and datapaths. Techniques such as machine learning and reinforcement learning can help predict performance, improve power efficiency, and optimize hardware resources. Its integratio...

Asynchronous multi-agent reinforcement learning for network-wide traffic signal control via stackelberg game prioritization

Reinforcement Learning with Value of Perfect Information Exploration

From Greedy Steps to Global Optimization: Learning Sequential Test Suite Generation

This paper formalizes test suite generation as a Markov Decision Process (MDP) and demonstrates that its objective exhibits monotone submodularity, which enables an effective relaxation of this NP-hard global optimization into a tractable step-wise greedy procedure.

Cultural Homogenisation in Artificial Intelligence and Social Media: The Role of Annotator Labour Bias and Global Consequences

The rapid growth of artificial intelligence (AI) and social media platforms has revolutionized global communication and creativity; however, it has also amplified concerns about cultural homogenization. These technologies are largely dominated by Western companies, which infuse cultural biases into AI frameworks and th...