DREAM-ON GYM: A Deep Reinforcement Learning Environment for Next-Gen Optical Networks

Nicolás Jara, Hermann Pempelfort, Erick Viera, Juan Pablo Sanchez, Gabriel España, Danilo Borquez-Paredes

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

1 Scopus citations

Abstract

A novel open-source toolkit for a straightforward implementation of deep reinforcement learning (DRL) techniques to address any resource allocation problem in current and future optical network architectures is presented. The tool follows OpenAI GYMNASIUM guidelines, presenting a versatile framework adaptable to any optical network architecture. Our tool is compatible with the Stable Baseline library, allowing the use of any agent available in the literature or created by the software user. For the training and testing process, we adapted the Flex Net Sim Simulator to be compatible with our toolkit. Using three agents from the Stable Baselines library, we exemplify our framework performance to demonstrate the tool’s overall architecture and assess its functionality. Results demonstrate how easily and consistently our tool can solve optical network resource allocation challenges using just a few lines of code applying Deep Reinforcement Learning techniques and ad-hoc heuristics algorithms.

Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Software Technologies, ICSOFT 2024
EditorsHans-Georg Fill, Francisco Jose Dominguez Mayo, Marten van Sinderen, Leszek Maciaszek, Leszek Maciaszek
PublisherSciTePress
Pages215-222
Number of pages8
ISBN (Electronic)9789897587061
DOIs
StatePublished - 2024
Externally publishedYes
Event19th International Conference on Software Technologies, ICSOFT 2024 - Dijon, France
Duration: 8 Jul 202410 Jul 2024

Publication series

NameProceedings of the 19th International Conference on Software Technologies, ICSOFT 2024

Conference

Conference19th International Conference on Software Technologies, ICSOFT 2024
Country/TerritoryFrance
CityDijon
Period8/07/2410/07/24

Keywords

  • Deep Reinforcement Learning
  • Framework
  • Optical Networks
  • Simulation Technique

Fingerprint

Dive into the research topics of 'DREAM-ON GYM: A Deep Reinforcement Learning Environment for Next-Gen Optical Networks'. Together they form a unique fingerprint.

Cite this