WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization
On the map: Mixture-of-experts → Expert routing strategies
also in 1 more
Abstract (arXiv)
Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traffic demand, and radio conditions challenge the scalability of conventional radio resource management (RRM). While offline reinforcement learning (RL) methods have demonstrated strong decision-making capabilities, learning a single policy that performs consistently across heterogeneous wireless environments remains difficult due to conflicting optimization objectives and limited model specialization. These challenges become particularly pronounced in coordinated multipoint (CoMP) transmission, where selecting the optimal serving-cell combination requires sequential decision-making under evolving network conditions. This paper presents the Wireless Sparse Decision Transformer with Mixture of Experts (WiSDoM), a sparse multi-task offline RL framework for adaptive multi-cell selection. WiSDoM combines Decision Transformers (DTs) with a Mixture-of-Experts (MoE) architecture that dynamically activates specialized experts according to task characteristics. This MoE mechanism improves model capacity without proportionally increasing inference cost, mitigates negative transfer, and enables expert specialization across tasks. WiSDoM is trained jointly on diverse network configurations spanning multiple base station and user equipment densities, mobility levels, and scheduler policies. Experimental results show that WiSDoM consistently outperforms heuristic methods, single-task models, and conventional multi-task DTs, improving quality of experience (QoE) by up to 55% while activating approximately one-third of the parameters of its dense counterpart during inference. Furthermore, WiSDoM exhibits strong task generalization and efficiently adapts to unseen wireless scenarios through few-shot prompting without retraining or fine-tuning.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Expert routing strategies, one of 12 directions in Mixture-of-experts. Builds on 27 of its 50 references that are in the map. First posted on arXiv 31 Aug 2026.
Builds on
27 of 50 references.
Closest ancestors · 1
Same direction, newest first
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity11 Jan
Other references · 26
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
- 2024Mixtral of Expertscited by 1,785
- 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
- 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 143
- 2026Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoningcited by 33
- 2023When should we prefer Decision Transformers for Offline Reinforcement Learning?cited by 20
- 2024WDMoE: Wireless Distributed Large Language Models with Mixture of Expertscited by 18
- 2024Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detectioncited by 16
- 2025Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformercited by 15
- 2024HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learningcited by 14
14 more
- 2024Decision Transformers for Wireless Communications: A New Paradigm of Resource Managementcited by 13
- 2023Empowering the 6G Cellular Architecture with Open RANcited by 10
- 2024Large Language Model-Driven Curriculum Design for Mobile Networkscited by 8
- 2024Multi-Modal Transformer and Reinforcement Learning-based Beam Managementcited by 8
- 2025Mixture-of-Experts Meets In-Context Reinforcement Learningcited by 7
- 2025Harnessing the Power of LLMs, Informers and Decision Transformers for Intent-driven RAN Management in 6Gcited by 6
- 2025Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Surveycited by 4
- 2020Generalized Coordinated Multipoint Framework for 5G and Beyondcited by 3
- 2024PandORA: Automated Design and Comprehensive Evaluation of Deep Reinforcement Learning Agents for Open RANcited by 3
- 2025Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoIcited by 3
- 2026Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocationcited by 3
- 2024Smart Jamming Attack and Mitigation on Deep Transfer Reinforcement Learning Enabled Resource Allocation for Network Slicingcited by 2
- 2026Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformerscited by 1
- 2026FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Executioncited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets
- 2026Offline Multi-Agent Reinforcement Learning for 6G Communications: Fundamentals, Applications and Future Directions
- 2026Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management
- 2026Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control
- 2024Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation
- 2025An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource Management
- 2025Optimal Expert Selection for Distributed Mixture-of-Experts at the Wireless Edge
- 2024An Overview of Machine Learning-Enabled Optimization for Reconfigurable Intelligent Surfaces-Aided 6G Networks: From Reinforcement Learning to Large Language Models