# Symbolic Reinforcement Learning for Safe RAN Control

arXiv: https://arxiv.org/abs/2103.06602 · HTML: https://mlsanity.com/paper/2103.06602/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 11 Mar 2021.

## Builds on (most cited first, 4 of 4)

- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes](https://mlsanity.com/paper/2001.03809/) (2020)
- [Off-policy Learning for Remote Electrical Tilt Optimization](https://mlsanity.com/paper/2005.10577/) (2020)
- [On the Timed Temporal Logic Planning of Coupled Multi-Agent Systems](https://mlsanity.com/paper/1709.06888/) (2017)

## Built on by (most cited first, 4 of 4)

- [Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding](https://mlsanity.com/paper/2112.11490/) (2021)
- [Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey](https://mlsanity.com/paper/2304.12090/) (2023)
- [Model Based Residual Policy Learning with Applications to Antenna Control](https://mlsanity.com/paper/2211.08796/) (2022)
- [Safe RAN control: A Symbolic Reinforcement Learning Approach](https://mlsanity.com/paper/2106.01977/) (2021)

## Abstract (arXiv)

In this paper, we demonstrate a Symbolic Reinforcement Learning (SRL) architecture for safe control in Radio Access Network (RAN) applications. In our automated tool, a user can select a high-level safety specifications expressed in Linear Temporal Logic (LTL) to shield an RL agent running in a given cellular network with aim of optimizing network performance, as measured through certain Key Performance Indicators (KPIs). In the proposed architecture, network safety shielding is ensured through model-checking techniques over combined discrete system models (automata) that are abstracted through reinforcement learning. We demonstrate the user interface (UI) helping the user set intent specifications to the architecture and inspect the difference in allowed and blocked actions.