# WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization

arXiv: https://arxiv.org/abs/2609.00284 · HTML: https://mlsanity.com/paper/2609.00284/

## Key facts

- No citing papers in the map yet (data through 14 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.

## Placed in

- Mixture-of-experts / [Expert routing strategies](https://mlsanity.com/moe/expert-routing-strategies/)
- Offline RL and imitation learning from data / [Offline multi-agent RL](https://mlsanity.com/offlinerl/offline-multi-agent-rl/)

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (2022)
- [Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2604.12374/) (2026)
- [When should we prefer Decision Transformers for Offline Reinforcement Learning?](https://mlsanity.com/paper/2305.14550/) (2023)
- [WDMoE: Wireless Distributed Large Language Models with Mixture of Experts](https://mlsanity.com/paper/2405.03131/) (2024)
- [Large Language Models in Wireless Application Design: In-Context Learning-enhanced Automatic Network Intrusion Detection](https://mlsanity.com/paper/2405.11002/) (2024)
- [Decision Transformers for Wireless Communications: A New Paradigm of Resource Management](https://mlsanity.com/paper/2404.05199/) (2024)
- [Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer](https://mlsanity.com/paper/2505.24378/) (2025)
- [HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.18080/) (2024)
- [Empowering the 6G Cellular Architecture with Open RAN](https://mlsanity.com/paper/2312.02746/) (2023)
- [Large Language Model-Driven Curriculum Design for Mobile Networks](https://mlsanity.com/paper/2405.18039/) (2024)
- [Multi-Modal Transformer and Reinforcement Learning-based Beam Management](https://mlsanity.com/paper/2410.19859/) (2024)
- [Mixture-of-Experts Meets In-Context Reinforcement Learning](https://mlsanity.com/paper/2506.05426/) (2025)
- [Harnessing the Power of LLMs, Informers and Decision Transformers for Intent-driven RAN Management in 6G](https://mlsanity.com/paper/2505.01841/) (2025)
- [Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Survey](https://mlsanity.com/paper/2504.19660/) (2025)
- [Generalized Coordinated Multipoint Framework for 5G and Beyond](https://mlsanity.com/paper/2008.06343/) (2020)
- [PandORA: Automated Design and Comprehensive Evaluation of Deep Reinforcement Learning Agents for Open RAN](https://mlsanity.com/paper/2407.11747/) (2024)
- [Attention-Enhanced Prompt Decision Transformers for UAV-Assisted Communications with AoI](https://mlsanity.com/paper/2505.22170/) (2025)
- [Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocation](https://mlsanity.com/paper/2602.16174/) (2026)
- [FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution](https://mlsanity.com/paper/2608.16157/) (2026)
- [Smart Jamming Attack and Mitigation on Deep Transfer Reinforcement Learning Enabled Resource Allocation for Network Slicing](https://mlsanity.com/paper/2410.05153/) (2024)
- [Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers](https://mlsanity.com/paper/2606.04328/) (2026)

## 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.