DDWCN: A Dual-Stream Dynamic Strategy Modeling Network for Multi-Agent Elastic Collaboration
Source abstract
Abstract
In the domain of multi-agent reinforcement learning, conventional algorithms such as VDN, QMIX, and QTRAN have exhibited favorable performance in static task scenarios. However, these algorithms encounter challenges due to their limited capacity to model elastic collaboration scenarios, wherein the number of agents and the state-action space undergo dynamic changes over time. To address this limitation, this paper proposes a novel multi-agent collaboration mechanism: the Dual-Stream Dynamic Weight Compensation Network (DDWCN). This method employs a dual-stream action modeling network for the classification and processing of actions. It integrates an information compensation network and a dynamic weight fusion network. These additions have been demonstrated to enhance the network’s robustness and generalization capabilities for complex collaborative tasks. Extensive experimentation on a variety of benchmark tasks in StarCraft II has validated the effectiveness of DDWCN. The findings indicate that this approach exhibits commendable scalability and reliability in authentic multi-agent collaboration scenarios, underscoring its extensive applicability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Collaboration in agile enterprises · Software Engineering Techniques and Practices · Multi-Agent Systems and Negotiation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic and Information Engineering, Inner Mongolia University, Hohhot 010021, China
Funding
Natural Science Foundation of Inner Mongolia Autonomous Region, China
References (34)
Show source-provided references
1. A survey of autonomous driving: Common practices and emerging technologies10.1109/ACCESS.2020.2983149 ↗
2. Multi-agent reinforcement learning for autonomous vehicles: A survey10.1007/s43684-022-00045-z ↗
3. Xia, B., Mantegh, I., and Xie, W. (2024). Decentralized UAV swarm control: A multi-layered architecture for integrated flight mode management and dynamic target interception. Drones, 8.10.3390/drones8080350 ↗
4. Wang, L., and Liu, G. (2024). Research on multi-robot collaborative operation in logistics and warehousing using A3C optimized YOLOv5-PPO model. Front. Neurorobot., 17.10.3389/fnbot.2023.1329589 ↗
5. Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications10.1109/TCYB.2020.2977374 ↗
6. Tan, M. (1993, January 27–29). Multi-agent reinforcement learning: Independent vs. cooperative agents. Proceedings of the Tenth International Conference on Machine Learning, Amherst, MA, USA.10.1016/B978-1-55860-307-3.50049-6 ↗
7. Boutilier, C. (1996, January 11–13). Planning, learning and coordination in multiagent decision processes. Proceedings of the TARK 1996, De Zeeuwse Stromen, The Netherlands.
8. Multi-agent actor-critic for mixed cooperative-competitive environments
9. Sunehag, P., Lever, G., Gruslys, A., Czarnecki, W.M., Zambaldi, V., Jaderberg, M., and Graepel, T. (2017). Value-decomposition networks for cooperative multi-agent learning. arXiv.
10. Monotonic value function factorisation for deep multi-agent reinforcement learning
11. Incorporating functional knowledge in neural networks
12. Son, K., Kim, D., Kang, W.J., Hostallero, D.E., and Yi, Y. (2019, January 9–15). Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA.
13. Wang, J., Ren, Z., Liu, T., Yu, Y., and Zhang, C. (2020). Qplex: Duplex dueling multi-agent Q-learning. arXiv.
14. Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning
15. Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., and Whiteson, S. (2018, January 2–7). Counterfactual multi-agent policy gradients. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA. No. 1.10.1609/aaai.v32i1.11794 ↗
16. Iqbal, S., and Sha, F. (2019, January 9–15). Actor-attention-critic for multi-agent reinforcement learning. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA.
17. The surprising effectiveness of PPO in cooperative multi-agent games
18. Kuba, J.G., Chen, R., Wen, M., Wen, Y., Sun, F., Wang, J., and Yang, Y. (2021). Trust region policy optimisation in multi-agent reinforcement learning. arXiv.
19. MAVEN: Multi-agent variational exploration
20. Wang, T., Gupta, T., Mahajan, A., Peng, B., Whiteson, S., and Zhang, C. (2020). RODE: Learning roles to decompose multi-agent tasks. arXiv.
21. Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10–15). Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. Proceedings of the International Conference on Machine Learning (ICML), Stockholm, Sweden.
22. FACMAC: Factored multi-agent centralised policy gradients
23. Yang, B., Gao, L., Zhou, F., Yao, H., Fu, Y., Sun, Z., and Ren, H. (2025). A coordination optimization framework for multi-agent reinforcement learning based on reward redistribution and experience reutilization. Electronics, 14.10.3390/electronics14122361 ↗
24. Zhao, Z., Zhang, Y., Wang, S., Zhou, Y., Zhang, R., and Chen, W. (2025). Assisted-value factorization with latent interaction in cooperate multi-agent reinforcement learning. Mathematics, 13.10.3390/math13091429 ↗
25. Liu, B., Liu, Q., Stone, P., Garg, A., Zhu, Y., and Anandkumar, A. (2021, January 18–24). Coach-player multi-agent reinforcement learning for dynamic team composition. Proceedings of the International Conference on Machine Learning (ICML), Virtual.
26. Wang, W., Yang, T., Liu, Y., Hao, J., Hao, X., Hu, Y., and Gao, Y. (2020, January 7–12). From few to more: Large-scale dynamic multi-agent curriculum learning. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
27. Tang, X., Xu, J., and Wang, S. (2022). Transferable multi-agent reinforcement learning with dynamic participating agents. arXiv.
28. Samvelyan, M., Rashid, T., De Witt, C.S., Farquhar, G., Nardelli, N., Rudner, T.G., and Whiteson, S. (2019). The StarCraft multi-agent challenge. arXiv.
29. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv.
30. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
31. Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer normalization. arXiv.
32. Liang, J., Miao, H., Li, K., Tan, J., Wang, X., Luo, R., and Jiang, Y. (2025). A Review of Multi-Agent Reinforcement Learning Algorithms. Electronics, 14.10.3390/electronics14040820 ↗
33. A review of cooperative multi-agent deep reinforcement learning10.1007/s10489-022-04105-y ↗
34. Double Q-learning