Speaker: Dr. Pedro P. Vergara (TU Delft)

Abstract: As the adoption of electric vehicles (EVs) accelerates, addressing the challenges of large-scale, city-wide optimization becomes critical to ensuring efficient use of charging infrastructure and maintaining electrical grid stability. This presentation introduces EV-GNN, a novel graph-based solution that addresses scalability challenges and captures uncertainties in EV behavior from a Charging Point Operator’s (CPO) perspective. We prove that EV-GNN enhances classic RL algorithms’ scalability and sample efficiency by combining an end-to-end Graph Neural Network (GNN) architecture with Reinforcement Learning (RL) and employing a branch pruning technique. We further demonstrate that the proposed architecture’s flexibility allows it to be combined with most state-of-the-art deep RL algorithms to solve a wide range of EV related problems, including those with continuous, multi-discrete, and discrete action spaces.

Date & Time: Thursday February 19, 2026 - 10:30am

Location: Auditorium R7, Building B28, Montefiore Institute