# Practical Policy Distillation for Reinforcement Learning in Radio Access Networks

arXiv: https://arxiv.org/abs/2511.06563 · HTML: https://mlsanity.com/paper/2511.06563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in On-policy and self-distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Placed in

- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)
- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 8 of 8)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Deep Learning-Based Channel Estimation](https://mlsanity.com/paper/1810.05893/) (2018)
- [Real-time Policy Distillation in Deep Reinforcement Learning](https://mlsanity.com/paper/1912.12630/) (2019)
- [Learning Robust Scheduling with Search and Attention](https://mlsanity.com/paper/2111.08073/) (2021)
- [Design Principles for Model Generalization and Scalable AI Integration in Radio Access Networks](https://mlsanity.com/paper/2306.06251/) (2023)
- [Generalization in Reinforcement Learning for Radio Access Networks](https://mlsanity.com/paper/2507.06602/) (2025)

## Abstract (arXiv)

Adopting artificial intelligence (AI) in radio access networks (RANs) presents several challenges, including limited availability of link-level measurements (e.g., CQI reports), stringent real-time processing constraints (e.g., sub-1 ms per TTI), and network heterogeneity (different spectrum bands, cell types, and vendor equipment). A critical yet often overlooked barrier lies in the computational and memory limitations of RAN baseband hardware, particularly in legacy 4th Generation (4G) systems, which typically lack on-chip neural accelerators. As a result, only lightweight AI models (under 1 Mb and sub-100~μ s inference time) can be effectively deployed, limiting both their performance and applicability. However, achieving strong generalization across diverse network conditions often requires large-scale models with substantial resource demands. To address this trade-off, this paper investigates policy distillation in the context of a reinforcement learning-based link adaptation task. We explore two strategies: single-policy distillation, where a scenario-agnostic teacher model is compressed into one generalized student model; and multi-policy distillation, where multiple scenario-specific teachers are consolidated into a single generalist student. Experimental evaluations in a high-fidelity, 5th Generation (5G)-compliant simulator demonstrate that both strategies produce compact student models that preserve the teachers' generalization capabilities while complying with the computational and memory limitations of existing RAN hardware.