A comparative study of reinforcement learning techniques to repair models

Barriga, Angela; Mandow, Lawrence; Cruz, José Luís Pérez de la; Rutle, Adrian; Heldal, Rogardt; Iovino, Ludovico

doi:10.1145/3417990.3421395

Cited by 9 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…choosing the action with highest Q-value) the remainder of the time. According to our testing (Barriga, Mandow, et al 2020), we obtain better results with an ε of 0.3. Regarding other parameters, discount factor (γ), and learning rate (α), we use 1.0 for both of them.…”

Section: Q(λ)mentioning

confidence: 81%

“…RL is a broad field with many algorithms. In previous work, we compared the performance of different RL algorithms in PARMOREL and Q(λ) was the one that provided us the best performance (Barriga, Mandow, et al 2020). Hence, we use Q(λ) in our current implementation.…”

Section: Learning Modulementioning

confidence: 99%

“…Therefore, the optimal convergence is usually achieved with an intermediate value of λ, which needs to be determined experimentally. According to our experiments (Barriga, Mandow, et al 2020), we get the best results by giving λ a value of 0.7. Lower or higher values lead to results of lower quality.…”

Section: Q(λ)mentioning

confidence: 99%

See 2 more Smart Citations

Addressing the trade off between smells and quality when refactoring class diagrams.

Barriga¹,

Bettini²,

Iovino³

et al. 2021

JOT

Self Cite

View full text Add to dashboard Cite

Models are core artifacts of modern software engineering processes, and they are subject to evolution throughout their life cycle due to maintenance and to comply with new requirements as any other software artifact. Smells in modeling are indicators that something may be wrong within the model design. Removing the smells using refactoring usually has a positive effect on the general quality of the model. However, it could have a negative impact in some cases since it could destroy the quality wanted by stakeholders. PARMOREL is a framework that, using reinforcement learning, can automatically refactor models to comply with user preferences. The work presented in this paper extends PARMOREL to support smells detection and selective refactoring based on quality characteristics to assure only the refactoring with a positive impact is applied. We evaluated the approach on a large available public dataset to show that PARMOREL can decide which smells should be refactored to maintain and, even improve, the quality characteristics selected by the user.

show abstract

Section: Q(λ)mentioning

confidence: 81%

Section: Learning Modulementioning

confidence: 99%

See 1 more Smart Citation

Addressing the trade off between smells and quality when refactoring class diagrams.

Barriga¹,

Bettini²,

Iovino³

et al. 2021

JOT

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since a metamodel is a model (in particular, a model of a model), some of these activities apply to both models and metamodels. For the sake of brevity, we only refer to models 12. The table is inevitably nonexhaustive and merely intended to reflect the kinds of activities and supporting approaches available.…”

mentioning

confidence: 99%

Collaborative model-driven software engineering

Ruscio

Franzago

Muccini

et al. 2018

Proceedings of the 40th International Conference on Software Engineering

View full text Add to dashboard Cite

Model-Driven Engineering (MDE) provides a huge body of knowledge of automation for many different engineering tasks, especially those involving transitioning from design to implementation. With the huge progress made on Artificial Intelligence (AI) techniques, questions arise for the future of MDE such as how existing MDE techniques and technologies can be improved or how other activities which currently lack dedicated support can also be automated. However, at the same time, it has to be revisited where and how models should be used to keep the engineers in the loop for creating, operating, and maintaining complex systems. To trigger dedicated research on these open points, we discuss the history of automation in MDE and present perspectives on how automation in MDE can be further improved and which obstacles have to be overcome in the medium and long term perspective.

show abstract

Comprehensive Systems: A formal foundation for Multi-Model Consistency Management

et al. 2021

Self Cite

View full text Add to dashboard Cite

Model management is a central activity in Software Engineering. The most challenging aspect of model management is to keep inter-related models consistent with each other while they evolve. As a consequence, there is a lot of scientific activity in this area, which has produced an extensive body of knowledge, methods, results and tools. The majority of these approaches, however, are limited to binary inter-model relations; i.e. the synchronisation of exactly two models. Yet, not every multi-ary relation can be factored into a family of binary relations. In this paper, we propose and investigate a novel comprehensive system construction, which is able to represent multi-ary relations among multiple models in an integrated manner and thus serves as a formal foundation for artefacts used in consistency management activities involving multiple models. The construction is based on the definition of partial commonalities among a set of models using the same language, which is used to denote the (local) models. The main theoretical results of this paper are proofs of the facts that comprehensive systems are an admissible environment for (i) applying formal means of consistency verification (diagrammatic predicate framework), (ii) performing algebraic graph transformation (weak adhesive HLR category), and (iii) that they generalise the underlying setting of graph diagrams and triple graph grammars.

show abstract

A comparative study of reinforcement learning techniques to repair models

Cited by 9 publications

References 17 publications

Addressing the trade off between smells and quality when refactoring class diagrams.

Addressing the trade off between smells and quality when refactoring class diagrams.

Collaborative model-driven software engineering

Comprehensive Systems: A formal foundation for Multi-Model Consistency Management

Contact Info

Product

Resources

About