Deep Reinforcement Learning Based Resource Allocation for V2V Communications
Open accessAbstract
In this paper, we develop a novel decentralized resource allocation mechanism for vehicle-to-vehicle (V2V) communications based on deep reinforcement learning, which can be applied to both unicast and broadcast scenarios. According to the decentralized resource allocation mechanism, an autonomous “agent,” a V2V link or a vehicle, makes its decisions to find the optimal sub-band and power level for transmission without requiring or having to wait for global information. Since the proposed method is decentralized, it incurs only limited transmission overhead. From the simulation results, each agent can effectively learn to satisfy the stringent latency constraints on V2V links while minimizing the interference to vehicle-to-infrastructure communications.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
One major obstacle associated with Deep-SHAP based SHAP values estimation is the considerable computational complexity, which increases exponentially with the number of state features and linearly with the number of background data samples.
“One major obstacle associated with the Deep-SHAP based SHAP values estimation is the considerable computational complexity, which increases exponentially with the number of state features and linearly with the number of background data samples [40].”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
The Discussion section discusses the computational complexity of the paper’s deep reinforcement-learning method, not Deep-SHAP. Searches for Deep-SHAP, SHAP values, background samples, and feature-attribution complexity found no passage addressing the claimed exponential or linear scaling. Page numbers were unavailable in our copy. (LLM, conf=0.78)
Experimental — accuracy not yet measuredSHAP provides a computationally efficient way to calculate Shapley values by iterating over a small subset of possible feature permutations using sampling approximations.
“As a remedy, SHAP provides a computationally efficient way to calculate Shapley values by iterating over a small subset of possible feature permutations using sampling approximations [40].”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
The Training and Testing Algorithms section describes sampling mini-batches for deep Q-learning, not sampling feature permutations to calculate Shapley values. The Discussion addresses computational complexity of the V2V resource-allocation method. Searches for SHAP, Shapley values, and feature-attribution sampling found no passage addressing the claim; page numbers were not available in our copy. (LLM, conf=0.78)
Experimental — accuracy not yet measuredDeep-SHAP is an extended version designed specifically for DNNs and adapts DeepLIFT algorithm to approximate Shapley values by linearizing the non-linear components of DNNs.
“Moreover, Deep Shapley additive explanation (Deep-SHAP) is an extended version designed specifically for DNNs and adapts DeepLIFT algorithm to approximate Shapley values by linearizing the non-linear components of DNNs [40].”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
The Deep Q-Learning section describes a neural network used to estimate Q-values for V2V resource allocation, not a method for explaining DNNs. Searches for Deep-SHAP, DeepLIFT, Shapley values, and feature attribution found no passage addressing the claimed method in our copy. (LLM, conf=0.78)
Experimental — accuracy not yet measuredDeepSHAP adds explainability to the DNNs by decomposing the output prediction of DNNs on a specific input by backpropagating the contributions of all neurons to every input feature.
“DeepSHAP adds explainability to the DNNs by decomposing the output prediction of DNNs on a specific input by backpropagating the contributions of all neurons to every input feature.”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
The Deep Q-Learning section (page unavailable) describes a DNN that produces Q-values, not a method for explaining its predictions. Searches for DeepSHAP, SHAP, feature attribution, and backpropagated contributions found no passage in our copy addressing the claim. (LLM, conf=0.78)
Experimental — accuracy not yet measuredInstead of using a single reference value, Deep-SHAP exploits a distribution of background samples such that the resulting Shapley values sum up to the difference between the expected model output on the passed background samples and the current model output.
“Instead of using a single reference value, Deep-SHAP exploits a distribution of background samples such that the resulting Shapley values sum up to the difference between the expected model output on the passed background samples and the current model output.”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
As the basis of our methodology, we leverage SHAP, a unified approach that offers a strong theoretically grounded framework for computing local and global explanations of a machine learning model.
“As the basis of our methodology, we leverage the SHAP [40], a unified approach that offers a strong theoretically grounded framework for computing local and global explanations of a machine learning model.”
From Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation (2025) · cites this paper as [40]
The Introduction and Deep Q-Learning sections describe a reinforcement-learning method for V2V resource allocation, not SHAP. Searches for SHAP, Shapley values, and model explanations found no passage in our copy addressing the cited description of SHAP. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · see citing works
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · see citing works
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · see citing works
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471 · see citing works
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · see citing works
The broadcast storm problem in a mobile ad hoc network
Ni, S.-Y., Tseng, Y., Chen, Y., et al. (1999) · doi:10.1145/313451.313525 · Cited by 3,156 · see citing works
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems
Ye, H., Li, G. Y., & Juang, B.-H. (2018) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2017.2757490 · Cited by 2,000 · see citing works
Self-citationResource Management with Deep Reinforcement Learning
Mao, H., Alizadeh, M., Menache, I., & Kandula, S. (2016) · Proceedings of the 15th ACM Workshop on Hot Topics in Networks · doi:10.1145/3005745.3005750 · Cited by 1,353 · see citing works
He, Y., Zhao, N., & Yin, H. (2018) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2017.2760281 · Cited by 569 · see citing works
Resource Allocation for D2D-Enabled Vehicular Communications
Liang, L., Li, G. Y., & Xu, W. (2017) · IEEE Transactions on Communications · doi:10.1109/tcomm.2017.2699194 · Cited by 409 · see citing works
Self-citationDevice-to-device communications in cellular networks
Feng, D., Lu, L., Yuan-Wu, Y., Li, G., Li, S., & Feng, G. (2014) · IEEE Communications Magazine · doi:10.1109/mcom.2014.6807946 · Cited by 385 · see citing works
Self-citationLTE evolution for vehicle-to-everything services
Seo, H., Lee, K.-D., Yasukawa, S., Peng, Y., & Sartori, P. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7497762 · Cited by 316 · see citing works
Vehicular Communications: A Network Layer Perspective
Peng, H., Liang, L., Shen, X., & Li, G. Y. (2018) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2018.2833427 · Cited by 306 · see citing works
Self-citationMachine learning for vehicular networks: Recent advances and application examples
Ye, H., Liang, L., Ye Li, G., Kim, J., Lu, L., & Wu, M. (2018) · IEEE Vehicular Technology Magazine · doi:10.1109/mvt.2018.2811185 · Cited by 303 · see citing works
Self-citationRadio Resource Management for D2D-Based V2V Communication
Sun, W., Ström, E. G., Brännström, F., Sou, K. C., & Sui, Y. (2015) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2015.2479248 · Cited by 274 · see citing works
A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs
Xu, Z., Wang, Y., Tang, J., Wang, J., & Gursoy, M. C. (2017) · International Conference on Communications · doi:10.1109/icc.2017.7997286 · Cited by 270 · see citing works
Vehicular Communications: A Physical Layer Perspective
Liang, L., Peng, H., Li, G. Y., & Shen, X. (2017) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2017.2750903 · Cited by 267 · see citing works
Self-citationDeep Reinforcement Learning for Resource Allocation in V2V Communications
Ye, H., & Li, G. Y. (2018) · 2018 IEEE International Conference on Communications (ICC) · doi:10.1109/icc.2018.8422586 · Cited by 222 · see citing works
Self-citationOn the Broadcast Storm Problem in Ad hoc Wireless Networks
Tonguz, O. K., Wisitpongphan, N., Parikh, J. S., et al. (2006) · International Conference on Broadband Communications, Networks and Systems (BROADNETS) · doi:10.1109/broadnets.2006.4374403 · Cited by 221 · see citing works
Recurrent deep neural networks for robust speech recognition
Weng, C., Yu, D., Watanabe, S., & Juang, B. H. (2014) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2014.6854661 · Cited by 126 · see citing works
Self-citationReinforcement learning for resource provisioning in the vehicular cloud
Salahuddin, M. A., Al‐Fuqaha, A., & Guizani, M. (2016) · IEEE Wireless Communications · doi:10.1109/mwc.2016.7553036 · Cited by 106 · see citing works
Coordinated Multi-Agent Reinforcement Learning in Networked Distributed POMDPs
Zhang, C., & Lesser, V. (2011) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v25i1.7886 · Cited by 98 · see citing works
Dynamic Proximity-Aware Resource Allocation in Vehicle-to-Vehicle (V2V) Communications
Ashraf, M. I., Bennis, M., Perfecto, C., & Saad, W. (2016) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/glocomw.2016.7848885 · Cited by 93 · see citing works
Machine Learning for Vehicular NetworksPreprint
Ye, H., Liang, L., Li, G. Y., Kim, J., Lu, L., & Wu, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.07143 · Cited by 43 · see citing works
Self-citationLow Complexity Outage Optimal Distributed Channel Allocation for Vehicle-to-Vehicle Communications
Bai, B. B., Chen, W., Letaief, K. B., et al. (2011) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2011.110116 · Cited by 39 · see citing works
Deep Reinforcement Learning based Distributed Resource Allocation for V2V Broadcasting
Ye, H., & Li, G. Y. (2018) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc.2018.8450518 · Cited by 35 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Applications of artificial intelligence and machine learning in smart cities
Ullah, Z., Al-Turjman, F., Mostarda, L., & Gagliardi, R. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.02.069 · Cited by 756 · see citing works
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future
Nawaz, S. J., Sharma, S. K., Wyne, S., Patwary, M. N., & Asaduzzaman, M. (2019) · IEEE Access · doi:10.1109/access.2019.2909490 · Cited by 658 · see citing works
Future Intelligent and Secure Vehicular Network Toward 6G: Machine-Learning Approaches
Tang, F., Kawamoto, Y., Kato, N., & Liu, J. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2954595 · Cited by 620 · see citing works
Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks
Nasir, Y. S., & Guo, D. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2933973 · Cited by 660 · see citing works
Single and multi-agent deep reinforcement learning for AI-enabled wireless networks: A tutorial
Feriani, A., & Hossain, E. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3063822 · Cited by 410 · see citing works
Zhang, X., Peng, M., Yan, S., & Sun, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2962715 · Cited by 282 · see citing works
Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective
Nguyen, D. C., Cheng, P., Ding, M., Lopez-Perez, D., Pathirana, P. N., Li, J., Seneviratne, A., Li, Y., & Poor, H. V. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3024783 · Cited by 160 · see citing works
Urmonov, O., Aliev, H., & Kim, H. (2023) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3197880 · Cited by 24 · see citing works
Multi-agent deep reinforcement learning based resource management in heterogeneous V2X networks
Zhao, J., Hu, F., Li, J., & Nie, Y. (2025) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.06.003 · Cited by 21 · see citing works
Explainable AI-Aided Feature Selection and Model Reduction for DRL-Based V2X Resource Allocation
Khan, N., Abdallah, A., Celik, A., Eltawil, A. M., & Coleri, S. (2025) · IEEE Transactions on Communications · doi:10.1109/tcomm.2025.3554655 · Cited by 20 · see citing works
Model Refinement Learning and an Example on Channel Estimation With Universal Noise Model
Wang, H.-M., Jiang, J.-C., & Wang, Y.-N. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036964 · Cited by 14 · see citing works
Reuse Distance-Aided Resource Selection Mechanisms for NR-V2X Sidelink Communication
Yin, J., & Hwang, S.-H. (2023) · Sensors · doi:10.3390/s24010253 · Cited by 14 · see citing works
Efficient and secure message authentication algorithm at the physical layer
Noura, H. N., Melki, R., Chehab, A., & Hernandez Fernandez, J. (2024) · Wireless Networks · doi:10.1007/s11276-020-02371-7 · Cited by 10 · see citing works
- Authors
- Ye, H., Li, G. Y., & Juang, B.-H. F.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- IEEE Transactions on Vehicular Technology
- Published
- 2019-04
- Volume
- 68
- Issue
- 4
- Pages
- 3163-3173
- ISSN
- 0018-9545 (ISSN-L)
- 1939-9359
- OpenAlex
- W2963000651
- Cited by
- 870
- References
- 28
- Citations by year
- 2026: 91 · 2025: 113 · 2024: 124 · 2023: 117 · 2022: 138 · 2021: 138 · 2020: 106 · 2019: 42 · 2012: 1
- FWCI
- 38.07
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- IEEE Transactions on Vehicular Technology (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1815637, 1731017)
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
- Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Keywords
- vehicle-to-vehicle communication, resource allocation, deep reinforcement learning, decentralized decision-making, sub-band allocation, power allocation, broadcast communication, unicast communication, delay constraints, autonomous vehicles
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
