reinforcement learning

Compact Reinforcement Learning: Resource-Efficient Formulations for Large-Scale Decision Making

Reinforcement learning (RL) offers a general framework for addressing problems involving sequential decision-making. However, modern practical applications of RL involve prohibitively large state and action sets: such as those in slate recommendations, image-based control, and large language-modeling tasks. Standard fo...

AI-driven whole-life costing for decision-ready UK public building retrofits

Abstract Public-sector building retrofits in the United Kingdom require decisions that balance whole-life cost, carbon reduction, service continuity and auditability under limited data and constrained capital budgets. This paper develops a decision-ready whole-life costing (WLC) workflow that integrates environmental,...

Reinforcement learning enhanced optimal experiment design for inverse problem in elasticity

Prediction-enhanced deep reinforcement learning for RIS-aided high-speed railway security under unknown eavesdropping

From rules to learning: A GIS-integrated agent-based reinforcement learning framework for simulating farmers’ land-use decisions and sustainable policy design

VirtuAI-Safe: Personalized Situated Safety Learning through Integration of VR and LLMs

Construction safety outcomes are strongly shaped by human factors, including how individuals perceive hazards, interpret contextual cues, and make safety-related decisions in dynamic work environments. Safety education therefore plays a critical role in preparing future construction professionals to reason about risk...

Deep reinforcement learning-based algorithm applied to drive control

Integrating Remote Sensing, Multi-Objective Optimization, and Agent-Based Modelling for Nature-Based Flood Mitigation

By 2030, pluvial flooding is estimated to cause nearly $500 billion in global damage, affecting 54 million people (UNDRR, 2015) each year. By 2050, metropolitan assets worth around $158 trillion could be at risk of floods. This rising risk has sparked an increased interest in nature-based solutions (NbS), as traditiona...

Emergence Conditions and Robustness Verification of Minimal Self-Awareness: A Systematic Study Based on Controlled Ablation Experiments

Abstract The origin of self-awareness is a fundamental issue at the intersection of cognitive science and artificial intelligence. Existing studies mostly focus on the operating mechanisms of higher-order consciousness, and lack systematic controlled experimental verification of the emergence conditions for the most ba...

Baselines, Sample Size, and Supervisory Activity in Guarded Reinforcement-Learning Traffic Signal Control: A SUMO Evidence Audit

Guarded supervision may leave a learned adviser inactive, obscuring non-inferiority. We audited an eight-version yellowSimulation of Urban MObility (SUMO) program covering three networks and 3480 counterfactual pairs. A contrast model gained 16.38 percentage points of root-mean-square-error skill over zero effect; eigh...

Gas-Flow-Rate Control Method of Solid-Rocket Ramjet Engines Based on Deep-Reinforcement Learning

The solid-rocket ramjet is a promising and critical propulsion component for propulsion systems in hypersonic vehicles. However, the gas-flow regulation system of the solid-rocket ramjet exhibits strong nonlinearity, time-varying parameters and abrupt operating-condition changes, which makes it challenging to design a...

Sustainable Approaches to Corrosion Protection in Reinforced Concrete: A Critical Review of Green Inhibitors, Surface Treatments, Self-Healing Systems, Nanomaterials, Smart Coatings, and Life-Cycle-Based Design

Corrosion of steel reinforcement is still the main reason reinforced concrete structures fail before the end of their planned service life. Every early repair costs money, and it also adds new cement, steel, and emissions. This review examines protection methods that can extend service life while lowering environmental...