Complex challenging decisions: delivering to customers while balancing timeliness and environmental cost; regulating peer-to-peer markets while fostering infrastructure investment; transitioning to electric mobility while ensuring fairness in the uncertain future. The STAR Lab team researches how technology – information and computation – can help people make better decisions in these kinds of complex situations.
We bring together data and models to solve complex combinatorial optimisation problems. By tackling real-world problems in socio-technical situations, we gain fundamental insights into the complementary interplay of machine learning and model-based search.
We design scalable computational models using micro-simulation, behavioural and spatial data, and participatory modelling, to understand the trade-offs of policy interventions, particularly in urban settings.
Journal of Air Transport Management, "Fleet Planning Under Demand and Fuel Price Uncertainty Using Actor-Critic Reinforcement Learning" (pdf)
IFAC 2023, "Robust Optimal Control With Inexact State Measurements and Adjustable Uncertainty Sets"
MT-ITS 2023, "Augmenting Ridership Data with Social Media Data to Analyse the Long-term Effect of COVID-19 on Public Transport"
ICAPS 2023, "Parallel Batch Processing for the Coating Problem"
ICAPS 2023, "Solving the Multi-Choice Two Dimensional Shelf Strip Packing Problem with Time Windows"
PLOS ONE, "Optimal Training of Integer-Valued Neural Networks with Mixed Integer Programming" (pdf)
CPAIOR 2023, "Predicting the Optimal Period for Cyclic Hoist Scheduling Problems" (pdf)
STAR Lab Director joins the editorial board of Urban Planning
STAR Lab Director will serve as Area Chair for ECAI 2023
AAMAS 2023, "Fair Pricing for Time-Flexible Smart Energy Markets"
Tom McDonald, MSc, graduated on "Mixed Integer (Non-)Linear Programming Formulations of Graph Neural Networks"
Imperial College London, "Linear and Bi-Linear Mixed Integer Formulations of Graph Neural Networks"
STAR Lab Director will serve as General Co-Chair for BNAIC/BeNeLearn 2023
Dirk van Bokkem, MSc, takes second place of the 2022 KNVI/KIVI Scriptieprijzen voor Informatica en Informatiekunde
STAR Lab Director will speak at the ELLIIT Focus Period Workshop on Hybrid AI
Flexible Services and Manufacturing, "Berth Planning and Real-Time Disruption Recovery: A Simulation Study for a Tidal Port" (pdf)
BNAIC 2022, "Machine Learning for the Cyclic Hoist Scheduling Problem" (pdf)
STAR Lab Director will serve as Proceedings and Video Co-Chair for RecSys 2023
BNAIC 2022, "Optimisation of Annual Planned Rail Maintenance" (journal abstract) (pdf)
IAAI 2023, "Embedding a Long Short-Term Memory Network in a Constraint Programming Framework for Tomato Greenhouse Optimisation" (preprint)
NeurIPS 2022, "Learning to Branch with Tree MDPs" (preprint)
Wouter Morssink, MSc, graduated on "Automatically Designing Diverse Golf Course Routings"
Data-driven building optimisation