A Cooperative Multi-Agent QTRAN Framework for Artificial Intelligence-Driven Cognitive V2X in the Internet of Vehicles
Source abstract
Abstract
Resource allocation for cognitive Vehicle-to-Everything (V2X) networks is challenging due to dynamic spectrum sharing, strong interference coupling, and stringent latency constraints for safety-critical Vehicle-to-Vehicle (V2V) traffic. Although recent Multi-Agent Reinforcement Learning (MARL) approaches report promising gains, many evaluations are conducted at limited and fixed network scales, which restricts insights into scalability under dense spectrum reuse. This paper investigates cooperative multi-agent learning for interference-aware and deadline-constrained V2X resource management. We propose a Q-value Transformation (QTRAN)-based value decomposition framework under centralized training with decentralized execution (CTDE) for joint resource-block and power allocation among V2V agents. The proposed approach is implemented in a realistic V2V/V2I simulator incorporating Manhattan grid mobility, fast fading, explicit cross-tier and co-channel interference, and per-link payload/deadline dynamics. Beyond communication-level performance, improved timely delivery of V2V safety messages can support cooperative maneuvering, collision avoidance, platooning, and infrastructure-assisted traffic management. Extensive simulations across varying numbers of V2V agents benchmark QTRAN against independent learning baselines including MARL and centralized single-agent learning (SARL). Results show that QTRAN improves performance compared with the selected learning baselines and enhances the throughput–reliability trade-off under interference-coupled spectrum reuse. For instance, at NV2V=20, QTRAN achieves a V2V rate of 0.194±0.004 and a V2I rate of 9.117±0.213, while reaching a V2V success rate of 0.812±0.017 with a low Deadline Miss Ratio of 0.001±0.000. At higher density (NV2V=50), QTRAN sustains strong reliability (V2V success rate of 0.719±0.006 and Completion Ratio of 0.716±0.006) while maintaining competitive infrastructure throughput (V2I rate of 9.251±0.114). These results indicate that QTRAN effectively captures non-linear interference interactions, enabling coordinated decentralized spectrum and power decisions under the adopted density-based evaluation setting, thereby enhancing V2V reliability and throughput in cognitive Internet of Vehicles.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Vehicular Ad Hoc Networks (VANETs) · Traffic control and management · Autonomous Vehicle Technology and Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mathematics and Computer Science, Research Laboratory on Computer Science’s Complex Systems (ReLa(CS)^{2}), University of Oum El Bouaghi, Oum El Bouaghi 04000, Algeria
Department of Computer Engineering (DISCA), Universitat Politècnica de València, 46022 València, Spain
Funding
MORELLINO · “Direcció General de Ciència i Investigació” Generalitat Valenciana-SPAIN · European Union’s Horizon Europe project REMARKABLE
References (40)
Show source-provided references
1. Pandian, A.P., Senjyu, T., Islam, S.M.S., and Wang, H. (2020). Enabling Technologies for Internet of Vehicles. Proceedings of the International Conference on Computer Networks, Big Data and IoT (ICCBI—2018), Springer.10.1007/978-3-030-24643-3 ↗
2. Campolo, C., Molinaro, A., Iera, A., Fontes, R.R., and Rothenberg, C.E. (2018). Towards 5G Network Slicing for the V2X Ecosystem. Proceedings of the 2018 4th IEEE Conference on Network Softwarization and Workshops (NetSoft), IEEE.10.1109/NETSOFT.2018.8459911 ↗
3. Survey on the internet of vehicles: Network architectures and applications10.1109/MCOMSTD.001.1900053 ↗
4. NeXt generation/dynamic spectrum access/cognitive radio wireless networks: A survey10.1016/j.comnet.2006.05.001 ↗
5. Wang, D., Qiu, A., Zhou, Q., and Schotten, H.D. (2025). A Survey on the Role of Artificial Intelligence and Machine Learning in 6G-V2X Applications. arXiv.10.1109/WF-IoT64238.2025.11270555 ↗
6. Boban, M., Kousaridas, A., Manolakis, K., Eichinger, J., and Xu, W. (2017). Use Cases, Requirements, and Design Considerations for 5G V2X. arXiv.
7. Bazzi, A., Cecchini, G., Menarini, M., Masini, B.M., and Zanella, A. (2019). Survey and Perspectives of Vehicular Wi-Fi versus Sidelink Cellular-V2X in the 5G Era. Future Internet, 11.10.3390/fi11060122 ↗
8. Human-level control through deep reinforcement learning10.1038/nature14236 ↗
9. Li, Y. (2018). Deep Reinforcement Learning: An Overview. arXiv.10.1201/9781351006620-1 ↗
10. Chen, J., Niedermeier, R., and Skowron, P. (2018). Stable Marriage with Multi-Modal Preferences. Proceedings of the EC ’18: 2018 ACM Conference on Economics and Computation, Association for Computing Machinery.10.1145/3219166.3219168 ↗
11. Soft actor–critic DRL for live transcoding and streaming in vehicular fog-computing-enabled IoV10.1109/JIOT.2020.3003398 ↗
12. Zhang, K., Yang, Z., and Başar, T. (2021). Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms. Handbook of Reinforcement Learning and Control, Springer International Publishing.10.1007/978-3-030-60990-0_12 ↗
13. Deep reinforcement learning for offloading and resource allocation in vehicle edge computing and networks10.1109/TVT.2019.2935450 ↗
14. Mean-field-aided multiagent reinforcement learning for resource allocation in vehicular networks10.1109/JIOT.2022.3214525 ↗
15. Delay constrained hybrid task offloading of internet of vehicle: A deep reinforcement learning method10.1109/ACCESS.2022.3206359 ↗
16. Son, K., Kim, D., Kang, W.J., Hostallero, D.E., and Yi, Y. (2019). Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. Proceedings of the International Conference on Machine Learning, PMLR.
17. Bouzoubia, R., Zaidi, S., Khamer, L., Bourouis, A., and Ogab, M. (2024). Deep reinforcement learning-based resource allocation for the Internet of Vehicles: A systematic mapping study. Proceedings of the International Conference on Computer Science’s Complex Systems and Their Applications, Springer.10.1007/978-3-031-90758-6_4 ↗
18. Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning10.1109/JSAC.2019.2933962 ↗
19. Jamal, M., Ullah, Z., Naeem, M., Abbas, M., and Coronato, A. (2024). A Hybrid Multi-Agent Reinforcement Learning Approach for Spectrum Sharing in Vehicular Networks. Future Internet, 16.10.3390/fi16050152 ↗
20. A survey on multi-agent reinforcement learning and its application
21. Zhou, Z., Liu, G., and Tang, Y. (2023). Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges. arXiv.
22. Artificial intelligence inspired transmission scheduling in cognitive vehicular communications and networks10.1109/JIOT.2018.2872013 ↗
23. Deep Reinforcement Learning Based Resource Allocation for V2V Communications10.1109/TVT.2019.2897134 ↗
24. Improvement of Maneuverability Within a Multiagent Fuzzy Transportation System with the Use of Parallel Biobjective Real-Coded Genetic Algorithm10.1109/TITS.2021.3115827 ↗
25. Prabuchandran, K.J., Hemanth Kumar, A.N., and Bhatnagar, S. (2014). Multi-agent reinforcement learning for traffic signal control. Proceedings of the 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), IEEE.10.1109/ITSC.2014.6958095 ↗
26. Rashid, T., Samvelyan, M., de Witt, C.S., Farquhar, G., Foerster, J., and Whiteson, S. (2018). QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. arXiv.
27. Ding, Y., Huang, Y., Tang, L., Qin, X., and Jia, Z. (2022). Resource Allocation in V2X Communications Based on Multi-Agent Reinforcement Learning with Attention Mechanism. Mathematics, 10.10.3390/math10193415 ↗
28. Federated Reinforcement Learning for Resource Allocation in V2X Networks10.1109/JSTSP.2024.3513692 ↗
29. Resource allocation strategy for vehicular communication networks based on multi-agent deep reinforcement learning
30. Zhang, W., Wu, Q., Fan, P., Wang, K., Cheng, N., Chen, W., and Letaief, K.B. (2025). Semantic-Aware Resource Management for C-V2X Platooning via Multi-Agent Reinforcement Learning. arXiv.
31. 3rd Generation Partnership Project (3GPP) (2019). Study on Evaluation Methodology of New Vehicle-to-Everything (V2X) Use Cases for LTE and NR, 3GPP. Technical Report TR 37.885.
32. 3GPP (2015). Evolved Universal Terrestrial Radio Access (E-UTRA); Further Advancements for E-UTRA Physical Layer Aspects, 3rd Generation Partnership Project (3GPP). See also versions v9.0.0–v9.2.0 on the 3GPP portal.
33. 3GPP (2017). Study on Channel Model for Frequencies from 0.5 to 100 GHz, 3rd Generation Partnership Project (3GPP). Version 14.0.0, Release 14.
34. A Mathematical Theory of Communication10.1002/j.1538-7305.1948.tb01338.x ↗
35. (2026, January 17). Kaggle. Available online: https://www.kaggle.com.
36. Meta-Reinforcement Learning Based Resource Allocation for Dynamic V2X Communications10.1109/TVT.2021.3098854 ↗
37. Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G
38. 3GPP (2016). Study on LTE-Based V2X Services, 3rd Generation Partnership Project. Technical Report TR 36.885.
39. Space division and theory of graph-coloration-based protocol for multi-channel multi-transceiver operation in Internet of Vehicles10.1186/s13638-025-02460-1 ↗
40. Road network layout based multi-hop broadcast protocols for Urban Vehicular Ad-hoc Networks10.1007/s11276-020-02531-9 ↗