Towards Explainable Reinforcement Learning in Optical Networks: The RMSA Use Case

• 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.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Telekommunikation (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Telecommunications (hsv//eng)

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Keyword

Explainable AI

Reinforcement learning

Routing, modulation format, and spectrum assignment

Publication and Content Type

kon (subject category)

ref (subject category)