Scenario-assisted Deep Reinforcement Learning

Raz Yerushalmi, Guy Amir, Achiya Elyasaf, David Harel, Guy Katz, Assaf Marron

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers. In this work-in-progress report, we propose a technique for enhancing the reinforcement learning training process (specifically, its reward calculation), in a way that allows human engineers to directly contribute their expert knowledge, making the agent under training more likely to comply with various relevant constraints. Moreover, our proposed approach allows formulating these constraints using advanced model engineering techniques, such as scenario-based modeling. This mix of black-box learning-based tools with classical modeling approaches could produce systems that are effective and efficient, but are also more transparent and maintainable. We evaluated our technique using a case-study from the domain of internet congestion control, obtaining promising results.

Original languageEnglish
Title of host publicationMODELSWARD 2022 - Proceedings of the 10th International Conference on Model-Driven Engineering and Software Development
EditorsEdwin Seidewitz
PublisherScience and Technology Publications, Lda
Pages310-319
Number of pages10
ISBN (Print)9789897585500
DOIs
StatePublished - 1 Jan 2022
Event10th International Conference on Model-Driven Engineering and Software Development, MODELSWARD 2022 - Virtual, Online
Duration: 6 Feb 20228 Feb 2022

Publication series

NameInternational Conference on Model-Driven Engineering and Software Development
ISSN (Electronic)2184-4348

Conference

Conference10th International Conference on Model-Driven Engineering and Software Development, MODELSWARD 2022
CityVirtual, Online
Period6/02/228/02/22

Keywords

  • Domain Expertise
  • Machine Learning
  • Rule-based Specifications
  • Scenario-based Modeling

ASJC Scopus subject areas

  • Software
  • Engineering (miscellaneous)

Fingerprint

Dive into the research topics of 'Scenario-assisted Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this