Background

REAL WORLD OPTIMISATION WITH LIFE-LONG LEARNING

Many practical problems arising in industrial domains concerned with operating sustainably, meeting demand and minimising costs cannot be solved exactly. Although many meta-heuristic optimisation techniques have been developed, it is clear that

  • There remains a worrying void between scientific research into optimisation techniques and those problems faced by end-users and addressed by commercial optimisation software vendors
  • Most approaches fail to recognise a crucial human competence; human beings continuously learn from experience . The failure of computational solvers to exploit previous knowledge both wastes useful knowledge and potentially hinders the discovery of good solutions

This proposal addresses these dual concerns raised above. We propose a novel lifelong-learning hyper-heuristic system which addresses current deficiencies inherent in current systems: it will exhibit short-term learning, producing fast and effective solutions to individual problems and at the same time, long-term learning processes will enable the system to autonomously adapt to new problem characteristics over time. Our research will be directly informed by real-world problems provided by two collaborators, accounting for real constraints and performance criteria.