Willem van Jaarsveld

Papers

Total Citations

H-Index

About

Willem van Jaarsveld is a leading researcher at the intersection of operations research and artificial intelligence, specializing in reinforcement learning (RL) for dynamic decision-making under uncertainty. His work focuses on developing and evaluating RL-based policies for complex logistical challenges, including inventory control and vehicle routing. In his highly cited 2025 paper, "Deep Controlled Learning for Inventory Control" (20 citations), van Jaarsveld pioneers the application of Deep Reinforcement Learning (DRL) to inventory management, critically analyzing why traditional DRL algorithms—designed for domains like game-playing—often fall short in this context. He proposes novel, tailored approaches that better account for the unique stochastic and sequential nature of supply chains. Complementing this, his 2024 study, "A comparison of reinforcement learning policies for dynamic vehicle routing problems with stochastic customer requests" (12 citations), provides a rigorous benchmark of neural network-based RL methods for dynamic vehicle routing problems (DVRPs). By systematically comparing policies that incorporate expected future consequences into current decisions, van Jaarsveld offers actionable insights for practitioners and a clear roadmap for future research. His work is instrumental in bridging the gap between cutting-edge AI and practical operations management, making him a key voice in the future of autonomous logistics.