Transfer Reinforcement Learning for Combinatorial Optimization Problems

Reinforcement learning is an important technique in various fields, particularly in automated machine learning for reinforcement learning (AutoRL). The integration of transfer learning (TL) with AutoRL in combinatorial optimization is an area that requires further research. This paper employs both A...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Algorithms Jg. 17; H. 2; S. 87
Hauptverfasser: Souza, Gleice Kelly Barbosa, Santos, Samara Oliveira Silva, Ottoni, André Luiz Carvalho, Oliveira, Marcos Santos, Oliveira, Daniela Carine Ramires, Nepomuceno, Erivelton Geraldo
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.02.2024
Schlagworte:
Algorithms
Analysis
Automation
Cities
Combinatorial analysis
combinatorial optimization
Computing time
Decision making
Empirical analysis
Knapsack problem
Machine learning
Management science
Markov analysis
Optimization
reinforcement learning
sequential ordering problem
Statistical analysis
transfer learning
Traveling salesman problem
Germany
ISSN:1999-4893, 1999-4893
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Reinforcement learning is an important technique in various fields, particularly in automated machine learning for reinforcement learning (AutoRL). The integration of transfer learning (TL) with AutoRL in combinatorial optimization is an area that requires further research. This paper employs both AutoRL and TL to effectively tackle combinatorial optimization challenges, specifically the asymmetric traveling salesman problem (ATSP) and the sequential ordering problem (SOP). A statistical analysis was conducted to assess the impact of TL on the aforementioned problems. Furthermore, the Auto_TL_RL algorithm was introduced as a novel contribution, combining the AutoRL and TL methodologies. Empirical findings strongly support the effectiveness of this integration, resulting in solutions that were significantly more efficient than conventional techniques, with an 85.7% improvement in the preliminary analysis results. Additionally, the computational time was reduced in 13 instances (i.e., in 92.8% of the simulated problems). The TL-integrated model outperformed the optimal benchmarks, demonstrating its superior convergence. The Auto_TL_RL algorithm design allows for smooth transitions between the ATSP and SOP domains. In a comprehensive evaluation, Auto_TL_RL significantly outperformed traditional methodologies in 78% of the instances analyzed.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1999-4893
1999-4893
DOI:10.3390/a17020087