Search Results for author: Giorgio Grani

Found 8 papers, 2 papers with code

Margin Optimal Classification Trees

1 code implementation19 Oct 2022 Federico D'Onofrio, Giorgio Grani, Marta Monaci, Laura Palagi

Thanks to their interpretability, decision trees have been intensively studied for classification tasks and, due to the remarkable advances in mixed integer programming (MIP), various approaches have been proposed to formulate the problem of training an Optimal Classification Tree (OCT) as a MIP model.

Binary Classification Classification +2

Solving the vehicle routing problem with deep reinforcement learning

no code implementations30 Jul 2022 Simone Foa, Corrado Coppola, Giorgio Grani, Laura Palagi

Comparisons between the algorithm proposed and the state-of-the-art solver OR-TOOLS show that the latter still outperforms the Reinforcement learning algorithm.

Combinatorial Optimization reinforcement-learning +1

PUSH: a primal heuristic based on Feasibility PUmp and SHifting

no code implementations30 Jul 2022 Giorgio Grani, Corrado Coppola, Valerio Agasucci

The main idea is to replace the rounding phase of the Feasibility Pump with a suitable adaptation of the Shifting and other rounding heuristics.

An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents

1 code implementation18 Oct 2021 Marta Monaci, Valerio Agasucci, Giorgio Grani

The aim is to build up a greedy-like heuristic able to learn on some distribution of JSSP instances, different in the number of jobs and machines.

Job Shop Scheduling reinforcement-learning +2

A network-based analysis of disease modules from a taxonomic perspective

no code implementations1 Apr 2021 Giorgio Grani, Lorenzo Madeddu, Paola Velardi

Proximity relationships of disease modules (hereafter DMs) in the human interactome network are now increasingly used in diagnostics, to identify pathobiologically similar diseases and to support drug repurposing and discovery.

Solving the single-track train scheduling problem via Deep Reinforcement Learning

no code implementations1 Sep 2020 Valerio Agasucci, Giorgio Grani, Leonardo Lamorgese

In these cases, it is the duty of human traffic controllers, the so-called dispatchers, to do their best to minimize the impact on traffic.

Q-Learning reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.