reinforcement learning

Intelligent Wireless EV Charging for Green Transportation: A Deep Reinforcement Learning Approach with Multi-Stage Current Battery Management

Electric vehicle (EV) wireless power transfer (WPT) systems face two fundamental challenges that hinder their widespread adoption: sensitivity to coil misalignment and the need for battery-friendly fast charging protocols. This paper presents a comprehensive and integrated framework that addresses both challenges throu...

Sample-Efficient Model-Based Reinforcement Learning for Autonomous Droplet Navigation via Controller Initialization

Model-based reinforcement learning (MBRL) is well suited to controlling physical systems that resist analytical modeling, but its reliance on real-world interaction makes data collection the dominant cost. This paper quantifies the effect of initialization choice on this cost, on a newly adapted robotic platform that g...

Research on Deep Reinforcement Learning-Driven Music Melody Generation Algorithms

Deploying artificial intelligence for occupational and environmental health in waste management: a systematic review

Objectives This systematic review examines how artificial intelligence (AI) mitigates occupational and environmental health risks in waste management, a sector where workers and communities face infectious, toxic, and physical hazards. Methods Following PRISMA guidelines, we systematically searched the SCOPUS database...

Codebase for Reinforcement Learning for Quantum Network Control with Application-Driven Objectives

A reinforcement learning (RL) framework written in C++ as a building block for quantum network control. The code implements the MDPs from the work titled "Reinforcement Learning for Quantum Network Control with Application-Driven Objectives," using policy gradients and the chain rule to optimize arbitrary non-linear ob...

Auditors, Not Oracles: Sparse Human Grounding for Bias-Aware Self-Alignment

Reinforcement learning from human feedback (RLHF) treats annotators as preference oracles. This is expensive and can encode annotator-pool bias into the reward signal: rater demographics, positional artifacts, and misspecified helpfulness criteria can become part of what the model is trained to produce. A growing body...

Lane-free signal control: simulator, controllers and result files

Code and result files behind a manuscript under anonymous review on signalcontrol for lane-free mixed traffic seen by a roadside camera. The archive contains a lane-free heterogeneous microscopic simulator with ajunction box, a pedestrian phase and a height-aware roadside camera thatpairs every camera frame with the tr...

Review on Modeling, Simulation, and Intelligent Control of Anaerobic Digestion for Food Waste Management

Anaerobic digestion (AD) is a promising technology for the valorization of food waste into renewable energy and nutrient-rich digestate while reducing greenhouse gas emissions. This review focus on the evolution of analysis models from mechanistic models like ADM1 and its extensions to data-driven and hybrid approaches...

Arabic Paraphrase Detection Using Transformers, Reinforcement Learning, and Ensemble Models

A data-driven model for stable long-horizon autoregressive prediction of plasma current and control-oriented boundary evolution in EAST

Accurate long-horizon prediction of tokamak plasma current, position, and boundary evolution is essential for magnetic control, rapid controller development, and reinforcement-learning-based optimization. However, high-fidelity physics-based simulators are often computationally prohibitive when large numbers of simulat...

Machine Learning–Driven Seismic Vulnerability Assessment of Prefabricated Concrete Beam–Column Joints Using High-Fidelity Simulations

Amanollahi Geodesic Curvature Flow Solver

We introduce the official open-access repository of the Amanollahi Geodesic Curvature Flow Solver, a breakthrough continuous optimization paradigm for Boolean Satisfiability (SAT) that definitively bridges a 40-year theoretical gap in pure continuous constraint satisfaction. Historically, continuous optimization framew...