mlsanityData to 14 Oct 2026

LOLLA: Deep Reinforcement Learning for Closed-Loop Link Adaptation Towards a GPU-Accelerated AI-RAN

arXiv 2606.23110 ↗First posted 22 Jun 2026eess.SP cs.LG cs.NIcited by 1

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Outer-loop link adaptation (OLLA) is widely deployed in 5G NR to track channel variations, yet its reliance on first-order, single-bit feedback degrades performance significantly under high-mobility and fast-varying channels. This paper presents LOLLA (Learned Outer-Loop Link Adaptation), a deep reinforcement learning framework that replaces the conventional OLLA staircase with a learned, continuous SINR offset conditioned on rich PHY/MAC telemetry inaccessible to OLLA. The offset modulates the SINR-to-MCS lookup table, preserving 3GPP-compliant MCS selection and provably subsuming the conventional OLLA update rule. A Proximal Policy Optimization (PPO) policy trained under a Lagrangian block error rate (BLER) constraint automatically enforces tunable reliability targets from 1% to 15% without manual penalty calibration. The framework is realized as the first closed-loop AI-native control dApp on a GPU-accelerated 5G NR stack, achieving end-to-end control latencies under 500 microseconds. Evaluations under 3GPP TDL channel models demonstrate 15% to 92% throughput gains over OLLA across Doppler frequencies up to 400 Hz, while attaining a Pareto frontier that strictly dominates OLLA across all evaluated reliability targets. The learned policy generalizes to unseen channel models and scales to eight concurrent UEs under shared-resource scheduling. In the uplink formulation, the gNB directly observes decoding outcomes, enabling simulation-to-deployment parity.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 27 of its 50 references that are in the map. First posted on arXiv 22 Jun 2026.

Builds on

27 of 50 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Generalization in Reinforcement Learning for Radio Access Networks9 Jul

Other references · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021Convex optimizationcited by 2,515
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  6. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 763
  7. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  8. 2018Residual Reinforcement Learning for Robot Controlcited by 274
  9. 2020Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPOcited by 186
  10. 2018Applications of Deep Reinforcement Learning in Communications and Networking: A Surveycited by 167
  11. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 151
  12. 2021The Road Towards 6G: A Comprehensive Surveycited by 40
14 more
  1. 2022dApps: Distributed Applications for Real-time Inference and Control in O-RANcited by 17
  2. 2025dApps: Enabling Real-Time AI-Based Open RAN Controlcited by 14
  3. 2020New Radio Physical Layer Abstraction for System-Level Simulations of 5G Networkscited by 7
  4. 2020Reinforcement Learning for Efficient and Tuning-Free Link Adaptationcited by 7
  5. 2024X5G: An Open, Programmable, Multi-vendor, End-to-end, Private 5G O-RAN Testbed with NVIDIA ARC and OpenAirInterfacecited by 6
  6. 2019Adaptive Modulation and Coding based on Reinforcement Learning for 5G Networkscited by 4
  7. 2021Massive MIMO Adaptive Modulation and Coding Using Online Deep Learning Algorithmcited by 4
  8. 2017Reinforcement learning techniques for Outer Loop Link Adaptation in 4G/5G systemscited by 2
  9. 2025InterfO-RAN: Real-Time In-band Cellular Uplink Interference Detection with GPU-Accelerated dAppscited by 2
  10. 2025Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial Testbedcited by 2
  11. 2026From Simulation to Reality: Practical Deep Reinforcement Learning-based Link Adaptation for Cellular Networkscited by 2
  12. 2025LibIQ: Toward Real-Time Spectrum Classification in O-RAN dAppscited by 1
  13. 2025Sim2Field: End-to-End Development of AI RANs for 6Gcited by 1
  14. 2025Joint Link Adaptation and Device Scheduling Approach for URLLC Industrial IoT Network: A DRL-based Method with Bayesian Optimizationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Improving 5G AI-RAN MCS Selection by Predicting Retransmissionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Online Learning-based Adaptive Beam Switching for 6G Networks: Enhancing Efficiency and Resilience
  2. 2025Towards Ultra-Reliable 6G in-X Subnetworks: Dynamic Link Adaptation by Deep Reinforcement Learning
  3. 2026EExApp: GNN-Based Reinforcement Learning for Radio Unit Energy Optimization in 5G O-RAN
  4. 2024Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation
  5. 2025Practical Policy Distillation for Reinforcement Learning in Radio Access Networks
  6. 2024Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications
  7. 2025Near-Real-Time Resource Slicing for QoS Optimization in 5G O-RAN using Deep Reinforcement Learning
  8. 2025QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning