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

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

2024

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.

Paper Citation

in Harvard Style

Jara N., Pempelfort H., Viera E., Sanchez J., España G. and Borquez-Paredes D. (2024). DREAM-ON GYM: A Deep Reinforcement Learning Environment for Next-Gen Optical Networks. In Proceedings of the 14th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH; ISBN 978-989-758-708-5, SciTePress, pages 215-222. DOI: 10.5220/0012715900003758

in Bibtex Style

@conference{simultech24,
author={Nicolás Jara and Hermann Pempelfort and Erick Viera and Juan Sanchez and Gabriel España and Danilo Borquez-Paredes},
title={DREAM-ON GYM: A Deep Reinforcement Learning Environment for Next-Gen Optical Networks},
booktitle={Proceedings of the 14th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH},
year={2024},
pages={215-222},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012715900003758},
isbn={978-989-758-708-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH
TI - DREAM-ON GYM: A Deep Reinforcement Learning Environment for Next-Gen Optical Networks
SN - 978-989-758-708-5
AU - Jara N.
AU - Pempelfort H.
AU - Viera E.
AU - Sanchez J.
AU - España G.
AU - Borquez-Paredes D.
PY - 2024
SP - 215
EP - 222
DO - 10.5220/0012715900003758
PB - SciTePress