Multi-Agent Deep Reinforcement Learning for Enhancement of Distributed Resource Allocation in Vehicular Network
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
To solve a decentralized radio resource management problem in a 5G vehicular network, we propose a novel resource allocation algorithm based on a multiagent deep reinforcement learning (MARL). We let each vehicle act as an individual agent that can select a unique combination of transport block (TB) and transmission power to broadcast periodic packets. Agent explores the environment and collects observations that later will be used to find the best combination of TB and transmission power. We apply an actor-critic reinforcement learning technique to choose optimal TB for each agent. To eliminate a nonstationarity in a multiagent setting, we utilize a centralized training that allows all agents to share their observations over critic networks. The information shared through critic network can assist each agent to learn the policies of other agents. In a decentralized execution, each agent may only use its actor network and local observation to find the most appropriate TB in the given level of transmission power. While training, the actions taken by actor are evaluated by corresponding critic that maps Q-value for all feasible actions in the given state. Our method results in 18% higher packet reception ratio than a spectrum allocation scheme based on a double DQN. The proposed method achieves 33% higher reward than the previous state-of-the-art that is also based on MARL.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
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 · cited 2×
“Using deep reinforcement learning (DRL), resource allocation in C-V2X network also can be effectively solved [10], [11].”
BackgroundMastering 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 · cited 2×
“Usingdeepreinforcementlearning(DRL),resourceallocation inC-V2Xnetworkalsocanbeeffectivelysolved[10],[11].”
(1999) · Cited by 5,147
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., & Mordatch, I. (2017) · arXiv · doi:10.48550/arxiv.1706.02275 · Cited by 3,377 · cited 3×
“Thus, in [24], each agent can utilize global states and actions during the training to get the policies of partner/competitors agents.”
BackgroundMethodDeterministic Policy Gradient Algorithms
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., & Riedmiller, M. (2014) · HAL · Cited by 3,275
Bellman, R. (1957) · Indiana University Mathematics Journal · doi:10.1512/iumj.1957.6.56038 · Cited by 2,408 · cited 1×
“A partially observable Markov game for multiagent settings with N different agents is defined by a set of states S which describes all feasible configurations, a set of actions A 1 , . . . , A N and a set of observations O 1 , . . . , O N of all agents [26].”
BackgroundMulti-Agent Reinforcement Learning: Independent vs. Cooperative Agents
Tan, M. (1993) · Machine Learning Proceedings 1993 · doi:10.1016/b978-1-55860-307-3.50049-6 · Cited by 1,810
Meinilä, J., Kyösti, P., Jämsä, T., & Hentilä, L. (2009) · Radio Technologies and Concepts for IMT‐Advanced · doi:10.1002/9780470748077.ch3 · Cited by 1,154
Multiagent cooperation and competition with deep reinforcement learning
Tampuu, A., Matiisen, T., Kodelja, D., Kuzovkin, I., Korjus, K., Aru, J., Aru, J., & Vicente, R. (2017) · PLOS ONE · doi:10.1371/journal.pone.0172395 · Cited by 877 · cited 1×
“In such condition, DDQN experiences nonstationary issue [13] and overfits a Q-function.”
BackgroundDeep Reinforcement Learning Based Resource Allocation for V2V Communications
Ye, H., Li, G. Y., & Juang, B.-H. F. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2897134 · Cited by 870
Research works printed but not linked: 4
- 10.1371/journal.pone.0172395 · DOI · Paper page
- Foerster, 2017, Stabilizing experience replay for deep multi-agent reinforcement learning
- Jan, Policy gradient methods for robotics, 2219
- Jan, 2008, Natural actor-critic, Neurocomputing, 71, 1180
Cited by
From 5G to 6G Networks: A Survey on AI-Based Jamming and Interference Detection and Mitigation
Lohan, P., Kantarcı, B., Ferrag, M. A., Tihanyi, N., & Shi, Y. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3416808 · Cited by 93
A Survey on Multi-Agent Reinforcement Learning Applications in the Internet of Vehicles
Mianji, E. M., Fardad, M., Muntean, G., & Tal, I. (2024) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2024-spring62846.2024.10683524 · Cited by 23
“[17]–[19]. actor and a centralized critic, and counterfactual multi-agent policy gradients (COMA).”
BackgroundContext-aware resource allocation for vehicle-to-vehicle communications in cellular-V2X networks
Zhang, F., & Wang, G. (2024) · Ad Hoc Networks · doi:10.1016/j.adhoc.2024.103582 · Cited by 26
Ning, P., Wang, H., Tang, T., Zhang, J., Du, H., Niyato, D. T., & Yu, F. R. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3525410 · Cited by 22
“To optimize the V2V link capacity and packet reception ratio in a 5G vehicular network, Urmonov et al. [20] proposed a decentralized radio resource management algorithm based on MARL with actor-critic style, in which each vehicle acts as an independent agent to find the optimal combination of…”
Zhao, J., Gao, X., Wu, Z., Zhang, Q., & Han, H. (2024) · Physical Communication · doi:10.1016/j.phycom.2024.102484 · Cited by 17
Metadata
- Authors
- Urmonov, O., Aliev, H., & Kim, H.
- Affiliations
- Chungbuk National University (KR)
- Venue
- IEEE Systems Journal
- Published
- 2023-03
- Volume
- 17
- Issue
- 1
- Pages
- 491-502
- ISSN
- 1932-8184 (ISSN-L)
- 1937-9234
- 2373-7816
- OpenAlex
- W4293731539
- Semantic Scholar
- d368f8151bffdcd45d3ba80c49cf63161bf194be
- Cited by
- 24
- References
- 26
- Citations by year
- 2026: 8 · 2025: 7 · 2024: 8 · 2023: 1
- FWCI
- 1.10
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Systems Journal (publishedVersion)
- Funders
- Regional Leading Research Center
- National Research Foundation of Korea (2022R1A5A8026986)
- Institute of Information & communications Technology Planning & Evaluation (No.2020-0-01304)
- Development of Self-Learnable Mobile Recursive Neural Network Processor Technology
- Ministry of Science and ICT, Korea (IITP-2022-2020-0-01462)
- Institute or Information and communications Technology Planning and Evaluation
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Vehicular Ad Hoc Networks (VANETs)
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Computer Science › Computer Networks and Communications › Cognitive Radio Networks and Spectrum Sensing
- Keywords
- multi-agent deep reinforcement learning, radio resource allocation, vehicular networks, 5G, transmission power control, actor-critic, centralized training decentralized execution, non-stationarity, packet reception rate, spectrum allocation
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Multi-Agent Deep Reinforcement Learning for Enhancement of Distributed Resource Allocation in Vehicular Network. https://app.cochat.ai/papers/10.1109/jsyst.2022.3197880
- The paper
- Urmonov, O., Aliev, H., & Kim, H. (2023). Multi-Agent Deep Reinforcement Learning for Enhancement of Distributed Resource Allocation in Vehicular Network. IEEE Systems Journal. https://doi.org/10.1109/jsyst.2022.3197880
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.