Samuel Moniz

Modelling Reinforcement Learning Scheduling Agents: Action spaces, reward designs, and expert demonstrations

Alexandre Jesus, Arthur Corrêa, Miguel Vieira, Catarina Marques et autres

pt (code pays fourni par la source)

Improving Cross-Problem Vehicle Routing with Locally Augmented Preferences and Representation Disentanglement

Arthur Corrêa, Paulo Nascimento, Samuel Moniz

Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separate model for every variant. In spite of recent progress, current approaches remain limited on two fronts. On the …

FiLMMeD: Feature-wise Linear Modulation for Cross-Problem Multi-Depot Vehicle Routing

Arthur Corrêa, Paulo Nascimento, Samuel Moniz

Solving practical multi-depot vehicle routing problems (MDVRP) is a challenging optimization task central to modern logistics, increasingly driven by e-commerce. To address the MDVRP's computational complexity, neural-based combinatorial optimization methods offer a promising scalable alternative to traditional approaches. However, neural-based methods typically …

FiLMMeD: Feature-wise Linear Modulation for Cross-Problem Multi-Depot Vehicle Routing

Arthur Corrêa, Paulo Nascimento, Samuel Moniz

Solving practical multi-depot vehicle routing problems (MDVRP) is a challenging optimization task central to modern logistics, increasingly driven by e-commerce. To address the MDVRP's computational complexity, neural-based combinatorial optimization methods offer a promising scalable alternative to traditional approaches. However, neural-based methods typically …

pt (code pays fourni par la source)

Socially responsible pharmaceutical supply chains for equitable access

Inês Duarte, Bruna Mota, Tânia Pinto‐Varela, Ana Amaro et autres

Equitable access to pharmaceuticals is essential to improve global health and quality of life. Achieving this requires the pharmaceutical industry to optimize its supply chains to balance social responsibility with economic viability and environmental sustainability. However, operating in a global environment presents …

pt (code pays fourni par la source)

A Constraint Programming Model for the Super-Agile Earth Observation Satellite Imaging Scheduling Problem

Margarida Caleiras, Samuel Moniz, Paulo Jorge Nascimento

As the dependence on satellite imaging continues to grow, modern satellites have become increasingly agile, with the new generation, namely super-agile Earth observation satellites (SAEOS), providing unprecedented imaging flexibility. The highly dynamic capabilities of these satellites introduce additional challenges to the scheduling …

pt (code pays fourni par la source)

Multi-task and transfer learning for scheduling flexible job-shops: Combining imitation, reinforcement, and preference optimization

Alexandre Jesus, Paulo Nascimento, Samuel Moniz

Unraveling the Rainbow: can value-based methods schedule?

Arthur Jorge Pereira Corrêa, Alexandre Jesus, Cristóvão Silva, Samuel Moniz

In this work, we conduct an extensive empirical study of several deep reinforcement learning algorithms on two challenging combinatorial optimization problems: the job-shop and flexible job-shop scheduling problems, both fundamental challenges with multiple industrial applications. Broadly, deep reinforcement learning algorithms fall into …

Tunensearch: A Hybrid Transfer Learning and Local Search Approach for Solving Vehicle Routing Problems

Arthur Jorge Pereira Corrêa, Cristóvão Silva, Liming Xu, Alexandra Brintrup et autres

pt, gb (code pays fourni par la source)

Enhancing Multi-Agent Deep Reinforcement Learning for Flexible Job-Shop Scheduling Through Constraint Programming

Alexandre Jesus, Arthur Jorge Pereira Corrêa, Miguel Vieira, Catarina M. Marques et autres

pt (code pays fourni par la source)

Optimal decomposition approach for solving large nesting and scheduling problems of additive manufacturing systems

Paulo Jorge Nascimento, Cristóvão Silva, Carlos Henggeler Antunes, Samuel Moniz

This paper addresses the challenges associated with nesting and production scheduling in additive manufacturing (AM). The problem studied consists of grouping a set of parts into batches, which are then assigned to and sequenced across the available machines, guaranteeing the production of …

pt (code pays fourni par la source)

Nesting and scheduling optimization of additive manufacturing systems: Mapping the territory

M. C. A. Pinto, Cristóvão Silva, Matthias Thürer, Samuel Moniz

The application of Additive Manufacturing (AM) within industrial settings brings new challenges to operational research. This paper provides in-depth analyses of nesting and scheduling problems in the context of AM. Using bibliometric and systematic review methods, we map the progression of knowledge …

pt, de (code pays fourni par la source)