Towards Explainable Reinforcement Learning in Optical Networks: The RMSA Use Case
Paper i proceeding, 2024
We propose an approach to extract explanations from a trained reinforcement learning agent. Our analysis over three RMSA environment variations shows how the agent uses the input information, increasing our understanding of its learned policy.
Routing, modulation format, and spectrum assignment
Reinforcement learning
Explainable AI
Författare
Omran Ayoub
University of Applied Sciences and Arts of Southern Switzerland
Carlos Natalino Da Silva
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Paolo Monti
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Conference on Optical Fiber Communication, Technical Digest Series
W4I.6
9781957171326 (ISBN)
Optical Fiber Communications Conference and Exhibition (OFC)
San Diego, CA, USA,
San Diego, CA, USA,
Fotoniskt-Assisterad Hårdvara för Reservoarberäkning (HJÄRNA)
Vetenskapsrådet (VR) (2022-04798), 2023-01-01 -- 2026-12-31.
Styrkeområden
Informations- och kommunikationsteknik
Ämneskategorier
Telekommunikation
Kommunikationssystem
Datavetenskap (datalogi)
DOI
10.1364/OFC.2024.W4I.6