CoChat

Generative Network Design for Multi-Agent Coordination: A VAE-Assisted Deep RL Approach

Open access
Chen, Qiliang, Heydari, Babak · 2025 · Journal of Mechanical Design

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1115/1.4068796

Cites

73 of 73 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 73 references

Research works printed but not linked: 12

  1. 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
  2. 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
  3. Diederik P Kingma and Max Welling. "Auto-encoding variational bayes". In: arXiv preprint arXiv:1312.6114 (2013). · arXiv
  4. 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
  5. 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.
  6. 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.
  7. Babak Heydari, Ozlem Ergun, Rashmi Dyal-Chand, and Yakov Bart. Reengineering the Sharing Economy: Design, Policy, and Regulation. Cambridge University Press, 2023.
  8. 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
  9. Martin A Nowak. "Five rules for the evolution of cooperation". In: science 314.5805 (2006), pp. 1560-1563.
  10. 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.
  11. Thomas N Kipf and Max Welling. "Variational graph auto-encoders". In: arXiv preprint arXiv:1611.07308 (2016). · arXiv
  12. 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

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
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
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.