Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks
Authors:
- Lingyi WangLWLingyi Wang
- Rashed ShelimRSRashed Shelim
- Walid SaadWSWalid Saad
- Naren RamakrishnanNRNaren Ramakrishnan
Preprint
Abstract
Despite the popularity of reinforcement learning (RL) in wireless networks, existing approaches that rely on model-free RL (MFRL) and model-based RL (MBRL) are data inefficient and short-sighted. Such RL-based solutions cannot generalize to novel network states since they capture only statistical patterns rather than the underlying physics and logic from wireless data. These limitations become particularly challenging in complex wireless networks with high dynamics and long-term planning requirements. To address these limitations, in this paper, a novel dual-mind world model-based learning framework is proposed with the goal of optimizing completeness-weighted age of information (CAoI) in a challenging mmWave V2X scenario. Inspired by cognitive psychology, the proposed dual-mind world model encompasses a pattern-driven System 1 component and a logic-driven System 2 component to learn dynamics and logic of the wireless network, and to provide long-term link scheduling over reliable imagined trajectories. Link scheduling is learned through end-to-end differentiable imagined trajectories with logical consistency over an extended horizon rather than relying on wireless data obtained from environment interactions. Moreover, through imagination rollouts, the proposed world model can jointly reason network states and plan link scheduling. During intervals without observations, the proposed method remains capable of making efficient decisions. Extensive experiments are conducted on a realistic simulator based on Sionna with real-world physical channel, ray-tracing, and scene objects with material properties. Simulation results show that the proposed world model achieves a significant improvement in data efficiency and achieves strong generalization and adaptation to unseen environments, compared to the state-of-the-art RL baselines, and the world model approach with only System 1.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks2025
- Mastering diverse control tasks through world modelsNature, 2025
- Artificial General Intelligence (AGI)-Native Wireless Systems: A Journey Beyond 6GProceedings of the IEEE, 2025
- Integrating Optimization Theory with Deep Learning for Wireless Network DesignIEEE Communications Magazine, 2025
- A Survey of Recent Advances in Optimization Methods for Wireless CommunicationsIEEE Journal on Selected Areas in Communications, 2024
- Robust Energy Efficient Beamforming Design for ISAC Full-Duplex Communication SystemsIEEE Wireless Communications Letters, 2024
- A Survey on Model-Based, Heuristic, and Machine Learning Optimization Approaches in RIS-Aided Wireless NetworksIEEE Communications Surveys & Tutorials, 2023
- Model-Based Deep Reinforcement Learning Framework for Channel Access in Wireless NetworksIEEE Internet of Things Journal, 2023
- Machine Learning for Large-Scale Optimization in 6G Wireless NetworksIEEE Communications Surveys & Tutorials, 2023
- Fast MIMO Beamforming via Deep Reinforcement Learning for High Mobility mmWave ConnectivityIEEE Journal on Selected Areas in Communications, 2021