Collaborative truck–robot deliveries: challenges, models, and methods
Robot-based urban last-mile deliveries have recently attracted increasing attention from
scientific research and industry. In particular, truck–robot delivery models are emerging as …
scientific research and industry. In particular, truck–robot delivery models are emerging as …
[HTML][HTML] A graph reinforcement learning framework for neural adaptive large neighbourhood search
Abstract Adaptive Large Neighbourhood Search (ALNS) is a popular metaheuristic with
renowned efficiency in solving combinatorial optimisation problems. However, despite 18 …
renowned efficiency in solving combinatorial optimisation problems. However, despite 18 …
Feature-based search space characterisation for data-driven adaptive operator selection
Combinatorial optimisation problems are known as unpredictable and challenging due to
their nature and complexity. One way to reduce the unpredictability of such problems is to …
their nature and complexity. One way to reduce the unpredictability of such problems is to …
Graph reinforcement learning for operator selection in the ALNS metaheuristic
ALNS is a popular metaheuristic with renowned efficiency in solving combinatorial
optimisation problems. However, despite 16 years of intensive research into ALNS, whether …
optimisation problems. However, despite 16 years of intensive research into ALNS, whether …
[HTML][HTML] Learning to Guide Local Search Optimisation for Routing Problems
Abstract Machine learning has shown promises in tackling routing problems yet falls short of
state-of-the-art solutions achieved by stand-alone operations research algorithms. This …
state-of-the-art solutions achieved by stand-alone operations research algorithms. This …
Q-Learning Based Framework for Solving the Stochastic E-waste Collection Problem
Abstract Electrical and Electronic Equipment (EEE) has evolved into a gateway for
accessing technological innovations. However, EEE imposes substantial pressure on the …
accessing technological innovations. However, EEE imposes substantial pressure on the …
Algorithm Parameters: Tuning and Control
AH Abdul Halim, S Das, I Ismail - Into a Deeper Understanding of …, 2025 - Springer
As mentioned in the previous chapter, the metaheuristic algorithms all have mostly static and
sometimes adaptive variables as default parameters. These parameters are denoted as …
sometimes adaptive variables as default parameters. These parameters are denoted as …
Cross-domain Selection Hyper-heuristics with Deep Reinforcement Learning
H Mayrhofer - 2025 - repositum.tuwien.at
While domain-specific heuristics are effective techniques for solving combinatorial
optimization problems, constructing adaptive methodologies that generalize across multiple …
optimization problems, constructing adaptive methodologies that generalize across multiple …
Check for updates GRAPH Reinforcement Learning for Operator Selection in the ALNS Metaheuristic
ALNS is a popular metaheuristic with renowned efficiency in solving combinatorial
optimisation problems. However, despite 16 years of intensive research into ALNS, whether …
optimisation problems. However, despite 16 years of intensive research into ALNS, whether …
[PDF][PDF] Deep Reinforcement Learning-driven Metaheuristics towards an AI Foundation Model for Multi-Objective Optimisation
FJWB van Oordt - research.tue.nl
Abstract This Master Thesis explores the generalisability of optimisation algorithms.
Although it's feasible to develop highly effective problem-specific methods for optimisation …
Although it's feasible to develop highly effective problem-specific methods for optimisation …