# Temporally Consistent Graph Q-Networks for Intelligent Network Control

arXiv: https://arxiv.org/abs/2606.13848 · HTML: https://mlsanity.com/paper/2606.13848/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.10800/) (2020)
- [Simplified Temporal Consistency Reinforcement Learning](https://mlsanity.com/paper/2306.09466/) (2023)
- [DRAG: Deep Reinforcement Learning Based Base Station Activation in Heterogeneous Networks](https://mlsanity.com/paper/1809.02159/) (2018)
- [Multi-agent Reinforcement Learning with Graph Q-Networks for Antenna Tuning](https://mlsanity.com/paper/2302.01199/) (2023)
- [A Graph Attention Learning Approach to Antenna Tilt Optimization](https://mlsanity.com/paper/2112.14843/) (2021)
- [Multi-agent Reinforcement Learning for Energy Saving in Multi-Cell Massive MIMO Systems](https://mlsanity.com/paper/2402.03204/) (2024)

## Abstract (arXiv)

Mobile networks continue to grow in complexity and next generation networks are expected to support both increasing traffic loads and more diverse services. As network complexity rises, optimizing antenna parameters under dynamic or changing objectives becomes increasingly challenging. We propose a novel multi-agent reinforcement learning (MARL) algorithm for high-level control and orchestration of mobile networks. The Temporally Consistent Graph Q-Network (TC-GQN) algorithm learns a self-predicting representation of the whole network that is task-independent and aggregates information from all base-stations. A graph neural network is trained using a global reward function to assign coordinated local actions based on the learned encoding of the global network state. We evaluate the algorithm in a simulated environment to orchestrate an energy-saving feature across multiple sectors and multiple carriers under different quality of service (QoS) constraints. The proposed algorithm outperforms state-of-the-art graph-based baselines and a competitive rule-based controller by improving hardware sleep time while maintaining QoS. Moreover, the learned representation enables rapid adaptation to changing intents.