Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach
Open accessThe DOI matches its Crossref record, with a small difference in title or year; 73 of the 73 references it cites were found in a registry or an index.
Abstract
We introduce a framework that integrates variational autoencoders (VAE) with reinforcement learning (RL) to balance system performance and resource usage in multi-agent systems by dynamically adjusting network structures over time. A key innovation of this method is its capability to handle the vast action space of the network structure. This is achieved by combining Variational Auto-Encoder and Deep Reinforcement Learning to control the latent space encoded from the network structures. The proposed method, evaluated on the modified OpenAI particle environment under various scenarios, not only demonstrates superior performance compared to baselines but also reveals interesting strategies and insights through the learned behaviors.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Our approach is complementary: information modulation can work synergistically with task allocation mechanisms, state observability can accelerate distributed learning in adaptive topologies [27], and transparency policies can amplify incentive-based mechanisms.”
From Adaptive Information Modulation: Designing Governance Mechanisms for Multi-Agent Artificial Intelligence Systems (2026) · cites this paper as [27]
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.
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
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Reinforcement Learning: An Introduction
Johnson, J. D., Li, J., & Chen, Z. (2000) · Neurocomputing · doi:10.1016/s0925-2312(00)00324-6 · Cited by 8,414
Graph Neural Networks: A Review of Methods and Applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2018) · arXiv · doi:10.48550/arxiv.1812.08434 · Cited by 6,880
Graph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
(1999) · Cited by 5,147
Generative Adversarial Networks: An Overview
Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., & Bharath, A. A. (2018) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2765202 · Cited by 4,540
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
Dueling Network Architectures for Deep Reinforcement Learning
Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., & de Freitas, N. (2015) · arXiv · doi:10.48550/arxiv.1511.06581 · Cited by 3,300
A Strategic Model of Social and Economic Networks
Jackson, M. O., & Wolinsky, A. (1996) · Journal of Economic Theory · doi:10.1006/jeth.1996.0108 · Cited by 2,588
Ray, P. P. (2023) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2023.04.003 · Cited by 2,463
Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control
Chu, T., Wang, J., Codeca, L., & Li, Z. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2901791 · Cited by 1,046
Supply chain network design under uncertainty: A comprehensive review and future research directions
Govindan, K., Fattahi, M., & Keyvanshokooh, E. (2017) · European Journal of Operational Research · doi:10.1016/j.ejor.2017.04.009 · Cited by 705
Sony, M., & Naik, S. (2020) · Technology in Society · doi:10.1016/j.techsoc.2020.101248 · Cited by 651
On Generative Spoken Language Modeling from Raw Audio
Lakhotia, K., Kharitonov, E., Hsu, W.-N., Adi, Y., Polyak, A., Bolte, B., Nguyen, T.-A., Copet, J., Baevski, A., Mohamed, A., et al. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00430 · Cited by 526
Learning Deep Generative Models of Graphs
Li, Y., Vinyals, O., Dyer, C., Pascanu, R., & Battaglia, P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.03324 · Cited by 385
Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
Jaakkola, T., Singh, S. P., & Jordan, M. I. (1994) · Cited by 361
A multi-agent based framework for supply chain risk management
Giannakis, M., & Louis, M. (2011) · Journal of Purchasing and Supply Management · doi:10.1016/j.pursup.2010.05.001 · Cited by 338
A Survey of Deep Reinforcement Learning in Video GamesPreprint
Shao, K., Tang, Z., Zhu, Y., Li, N., & Zhao, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10944 · Cited by 322
Action Branching Architectures for Deep Reinforcement Learning
Tavakoli, A., Pardo, F., & Kormushev, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11798 · Cited by 248
Managing engineering systems with large state and action spaces through deep reinforcement learning
Andriotis, C. P., & Papakonstantinou, K. G. (2019) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2019.04.036 · Cited by 222
Multi-vehicle routing problems with soft time windows: A multi-agent reinforcement learning approach
Zhang, K., He, F., Zhang, Z., Lin, X., & Li, M. (2020) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102861 · Cited by 217
Su, R., Zhang, D., Venkatesan, R., Gong, Z., Li, C., Ding, F., Jiang, F., & Zhu, Z. (2019) · IEEE Network · doi:10.1109/mnet.2019.1900024 · Cited by 201
Molecular design in drug discovery: a comprehensive review of deep generative models
Cheng, Y., Gong, Y., Liu, Y., Song, B., & Zou, Q. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab344 · Cited by 169
Multi-agent reinforcement learning for online scheduling in smart factories
Zhou, T., Tang, D., Zhu, H., & Zhang, Z. (2021) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2021.102202 · Cited by 156
A Systematic Survey on Deep Generative Models for Graph Generation
Guo, X., & Zhao, L. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3214832 · Cited by 151
A survey on text generation using generative adversarial networks
de Rosa, G. H., & Papa, J. P. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108098 · Cited by 129
Matheron, G., Perrin, N., & Sigaud, O. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61616-8_25 · Cited by 126
He, L., He, C., Reynolds, T. L., Bai, Q., Huang, Y., Li, C., Zheng, K., & Chen, Y. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocab047 · Cited by 110
State of the Art Control of Atari Games Using Shallow Reinforcement Learning
Liang, Y., Machado, M. C., Talvitie, E., & Bowling, M. (2016) · Adaptive Agents and Multi-Agents Systems · doi:10.5555/2936924.2936996 · Cited by 66
Network Modularity is essential for evolution of cooperation under uncertainty
Gianetto, D. A., & Heydari, B. (2015) · Scientific Reports · doi:10.1038/srep09340 · Cited by 61
Self-citationStrategic Behavior of Large Language Models: Game Structure vs. Contextual FramingPreprint
Lorè, N., & Heydari, B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.05898 · Cited by 56
Self-citationDecentralized and Centralized Planning for Multi-Robot Additive Manufacturing
Poudel, L., Elagandula, S., Zhou, W., & Sha, Z. (2022) · Journal of Mechanical Design · doi:10.1115/1.4055735 · Cited by 53
Optimization-Based Disassembly Sequence Planning Under Uncertainty for Human–Robot Collaboration
Liao, H., Chen, Y., Hu, B., & Behdad, S. (2022) · Journal of Mechanical Design · doi:10.1115/1.4055901 · Cited by 53
van der Zwet, K., Barros, A. I., van Engers, T., & Sloot, P. M. A. (2022) · Humanities and Social Sciences Communications · doi:10.1057/s41599-022-01082-y · Cited by 51
Leveraging Task Modularity in Reinforcement Learning for Adaptable Industry 4.0 Automation
Chen, Q., Heydari, B., & Moghaddam, M. (2021) · Journal of Mechanical Design · doi:10.1115/1.4049531 · Cited by 40
Self-citationFair Topologies: Community Structures and Network Hubs Drive Emergence of Fairness Norms
Mosleh, M., & Heydari, B. (2017) · Scientific Reports · doi:10.1038/s41598-017-01876-0 · Cited by 39
Self-citationResource-Constrained Scheduling for Multi-Robot Cooperative Three-Dimensional Printing
Poudel, L., Zhou, W., & Sha, Z. (2021) · Journal of Mechanical Design · doi:10.1115/1.4050380 · Cited by 34
Shibata, K., Jimbo, T., & Matsubara, T. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561274 · Cited by 34
Catalysts of Cooperation in System of Systems: The Role of Diversity and Network Structure
Gianetto, D. A., & Heydari, B. (2013) · IEEE Systems Journal · doi:10.1109/jsyst.2013.2284959 · Cited by 32
Self-citationA Systematic Survey on Deep Generative Models for Graph GenerationPreprint
Guo, X., & Zhao, L. (2020) · doi:10.36227/techrxiv.12733037.v1 · Cited by 32
A measure of heterogeneity in multi-agent systems
Twu, P., Mostofi, Y., & Egerstedt, M. (2014) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2014.6858632 · Cited by 29
System-of-systems approach to air transportation design using nested optimization and direct search
Marwaha, G., & Kokkolaras, M. (2014) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-014-1180-1 · Cited by 27
Efficient network structures with separable heterogeneous connection costs
Heydari, B., Mosleh, M., & Dalili, K. (2015) · Economics Letters · doi:10.1016/j.econlet.2015.06.014 · Cited by 26
Self-citationCtrl-Z: Recovering from Instability in Reinforcement LearningPreprint
Dasagi, V., Bruce, J., Peynot, T., & Leitner, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.03732 · Cited by 22
Xu, Z., Hong, C. S., Zurita, N. F. S., Gyory, J. T., Stump, G. M., Nolte, H., Cagan, J., & McComb, C. (2024) · Journal of Mechanical Design · doi:10.1115/1.4064490 · Cited by 22
Bijami, E., & Farsangi, M. M. (2018) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331218770493 · Cited by 21
Distributed Resource Management in Systems of Systems: An Architecture Perspective
Mosleh, M., Ludlow, P., & Heydari, B. (2016) · Systems Engineering · doi:10.1002/sys.21342 · Cited by 21
Self-citationComplexity and the notion of system of systems: part (I): general systems and complexity
Karcanias, N., & Hessami, A. G. (2010) · World Automation Congress (WAC) · Cited by 20
Sparse cliques trump scale-free networks in coordination and competition
Gianetto, D. A., & Heydari, B. (2016) · Scientific Reports · doi:10.1038/srep21870 · Cited by 20
Self-citationManaging engineering systems with large state and action spaces through deep reinforcement learningPreprint
Andriotis, C. P., & Papakonstantinou, K. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.02052 · Cited by 19
Micro-level social structures and the success of COVID-19 national policies
Cao, Q., & Heydari, B. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00314-0 · Cited by 18
Self-citationMulti-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning ApproachPreprint
Zhang, K., Li, M., Zhang, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05513 · Cited by 17
Resource allocation through network architecture in systems of systems: A complex networks framework
Mosleh, M., Ludlow, P., & Heydari, B. (2016) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon.2016.7490629 · Cited by 16
Self-citationChen, Q., & Heydari, B. (2022) · Journal of Mechanical Design · doi:10.1115/1.4055057 · Cited by 12
Self-citationEllis, J., Vassilev, I., James, E., & Rogers, A. E. (2020) · Implementation Science Communications · doi:10.1186/s43058-020-00087-5 · Cited by 9
Chamseddine, I. M., & Kokkolaras, M. (2017) · Journal of Mechanical Design · doi:10.1115/1.4036778 · Cited by 6
Joseph, K., Chen, H.-Y. W., Ionescu, S., Du, Y., Sankhe, P., Hannák, A., & Rudra, A. (2022) · Applied Network Science · doi:10.1007/s41109-022-00486-8 · Cited by 6
A Scalable Algorithm for Self-Organization in Event-Triggered Networked Control Systems
Ion, A., & Pătraşcu, M. (2019) · European Control Conference (ECC) · doi:10.23919/ecc.2019.8796112 · Cited by 5
The Sos Conductor: Orchestrating Resources With Iterative Agent-Based Reinforcement Learning
Chen, Q., & Heydari, B. (2024) · Systems Engineering · doi:10.1002/sys.21747 · Cited by 5
Self-citationOrorbia, M. E., & Warn, G. P. (2024) · Journal of Mechanical Design · doi:10.1115/1.4065488 · Cited by 5
van der Zwet, K., van Engers, T., de Barros, A. M. B., et al. (2021) · Research Square · doi:10.21203/rs.3.rs-845904/v1 · Cited by 4
Micro-level Social Structures and the Success of COVID-19 National PoliciesPreprint
Cao, Q., & Heydari, B. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3977156 · Cited by 4
Self-citationVirtual Network Control for Power Bills Reduction and Network Stability
Nakamura, R., Kawahara, R., Wakayama, T., & Harada, S. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3158400 · Cited by 4
An Integrated Single Framework for Text, Image and Voice for Sentiment Mining of Social Media Posts
Gubbala, K., & Sowjanya, A. M. (2022) · Revue d intelligence artificielle · doi:10.18280/ria.360305 · Cited by 4
Physics guided deep learning generative models for crystal materials discoveryPreprint
Zhao, Y., Siriwardane, E. M. D., & Hu, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.03528 · Cited by 3
Chen, Q., Ilami, S., Lore, N., & Heydari, B. (2026) · Journal of Mechanical Design · doi:10.1115/1.4070755 · Cited by 3
Self-citationDeep learning based network similarity for model selection
Singh, K. V., Verma, A. K., & Vig, L. (2021) · Data Science · doi:10.3233/ds-210033 · Cited by 2
Siciliano, M. D., & Whetsell, T. A. (2021) · arXiv (Cornell University) · Cited by 2
Image Captioning Generator Text-to-Speech
Sharma, T., Anand, N., Gaurav, K., & Kapoor, R. (2022) · INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING · doi:10.47164/ijngc.v13i3.669 · Cited by 2
Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation
Chen, Q., Ilami, S., Lore, N., & Heydari, B. (2024) · arXiv · Cited by 2
Self-citationOptimising SARS-CoV-2 pooled testing strategies on social networks for low-resource settings
Mazzitello, K. I., Jiang, Y., & Arizmendi, C. M. (2021) · Journal of Physics A Mathematical and Theoretical · doi:10.1088/1751-8121/ac039b · Cited by 2
Chaudhari, A. M., Gralla, E. L., Szajnfarber, Z., & Panchal, J. H. (2021) · ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC/CIE) · doi:10.1115/detc2021-71277 · Cited by 1
Research works printed but not linked: 12
- Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. "Au- togen: Enabling next-gen llm applications via multi-agent conversation framework". In: arXiv preprint arXiv:2308.08155 (2023). · arXiv
- Qiliang Chen, Nunzio Lore, Babak Heydari, et al. "Instigating Coop- eration among LLM Agents Using Adaptive Information Modulation". In: arXiv preprint arXiv:2409.10372 (2024). · arXiv
- Diederik P Kingma and Max Welling. "Auto-encoding variational bayes". In: arXiv preprint arXiv:1312.6114 (2013). · arXiv
- Guillaume Matheron, Nicolas Perrin, and Olivier Sigaud. "The problem with DDPG: understanding failures in deterministic environments with sparse rewards". In: arXiv preprint arXiv:1911.11679 (2019). · arXiv
- Mohsen Mosleh, Peter Ludlow, and Babak Heydari. "Distributed re- source management in Systems of Systems: An architecture perspec- tive". In: Systems Engineering 19.4 (2016), pp. 362-374.
- Laiyang Ke, Daniel T. O'Brien, and Babak Heydari. "Airbnb and neighborhood crime: The incursion of tourists or the erosion of local social dynamics?" In: PLoS one 16.7 (2021), e0253315.
- Babak Heydari, Ozlem Ergun, Rashmi Dyal-Chand, and Yakov Bart. Reengineering the Sharing Economy: Design, Policy, and Regulation. Cambridge University Press, 2023.
- Garry Robins, Dean Lusher, Chiara Broccatelli, David Bright, Colin Gallagher, Maedeh Aboutalebi Karkavandi, Petr Matous, James Coutinho, Peng Wang, Johan Koskinen, Bopha Roden, and Giovanni Radhitio Putra Sadewo. "Multilevel network interventions: Goals, actions, and outcomes". In: Social Networks 72 (2023), pp. 108-120. issn: 0378- 8733. doi: https : / / doi . org / 10 . 1016 / j . socnet . 2022 . 09 . 005. url: https : / / www . sciencedirect . com / science / article / pii / S0378873322000867. · doi:10.1016/j.socnet.2022.09.005.url:https://www.sciencedirect.com/science/article/pii/s0378873322000867
- Martin A Nowak. "Five rules for the evolution of cooperation". In: science 314.5805 (2006), pp. 1560-1563.
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. "Gen- erative adversarial networks". In: Communications of the ACM 63.11 (2020), pp. 139-144.
- Thomas N Kipf and Max Welling. "Variational graph auto-encoders". In: arXiv preprint arXiv:1611.07308 (2016). · arXiv
- Yibo Li, Jianfeng Pei, and Luhua Lai. "Structure-based de novo drug design using 3D deep generative models". In: Chemical science 12.41 (2021), pp. 13664-13675.
Cited by
Generative AI for O-RAN Slicing: A Semi-Supervised Approach with VAE and Contrastive LearningPreprint
Nouri, S., Motalleb, M. K., Shah‐Mansouri, V., & Shariatpanahi, S. P. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.08861 · Cited by 5
Chen, Q., Ilami, S., Lore, N., & Heydari, B. (2026) · Journal of Mechanical Design · doi:10.1115/1.4070755 · Cited by 3
Self-citationChen, M., & Shen, Y. (2026) · Engineering Structures · doi:10.1016/j.engstruct.2026.122908 · Cited by 1
Çetinkaya, İ. O., Khodadadian, S., & Topcu, T. G. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.08.188 · Cited by 1
Inverse Design for Additive Manufacturing Driven by Thermal-Induced Distortion
Wang, W., Li, H., Yang, L., Wang, Z., Du, D., & Jiang, L. (2026) · Journal of Mechanical Design · doi:10.1115/1.4071306
Metadata
- Authors
- Chen, Q., & Heydari, B.
- Affiliations
- ss: 360 Huntington Ave. Boston, MA 02135
- 360 Huntington Avenue 334 SN Boston, MA 02215
- Corresponding author
- Chen, Qiliang
- Heydari, Babak
- Venue
- Journal of Mechanical Design
- Publisher
- ASME International
- Published
- 2025-05-29
- Pages
- 1-57
- ISSN
- 0161-8458 (ISSN-L)
- 1050-0472
- 1528-9001
- OpenAlex
- W4410852487
- Cited by
- 4
- References
- 66
- Citations by year
- 2026: 4
- FWCI
- 1.62
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Journal of Mechanical Design (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Keywords
- multi-agent coordination, variational autoencoder, deep reinforcement learning, dynamic network structure, latent space control
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
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.