Safe RAN control: A Symbolic Reinforcement Learning Approach

no code implementations • 3 Jun 2021 • Alexandros Nikou, Anusha Mujumdar, Vaishnavi Sundararajan, Marin Orlic, Aneta Vulgarakis Feljan

In particular, we provide a purely automated procedure in which a user can specify high-level logical safety specifications for a given cellular network topology in order for the latter to execute optimal safe performance which is measured through certain Key Performance Indicators (KPIs).

reinforcement-learning Reinforcement Learning (RL) +1

Symbolic Reinforcement Learning for Safe RAN Control

no code implementations • 11 Mar 2021 • Alexandros Nikou, Anusha Mujumdar, Marin Orlic, Aneta Vulgarakis Feljan

In this paper, we demonstrate a Symbolic Reinforcement Learning (SRL) architecture for safe control in Radio Access Network (RAN) applications.

reinforcement-learning Reinforcement Learning (RL)

Machine Reasoning Explainability

no code implementations • 1 Sep 2020 • Kristijonas Cyras, Ramamurthy Badrinath, Swarup Kumar Mohalik, Anusha Mujumdar, Alexandros Nikou, Alessandro Previti, Vaishnavi Sundararajan, Aneta Vulgarakis Feljan

As a field of AI, Machine Reasoning (MR) uses largely symbolic means to formalize and emulate abstract reasoning.

Explainable Artificial Intelligence (XAI)

Antifragility for Intelligent Autonomous Systems

no code implementations • 26 Feb 2018 • Anusha Mujumdar, Swarup Kumar Mohalik, Ramamurthy Badrinath

Antifragile systems grow measurably better in the presence of hazards.