Coordination and Robustness in Multi-Agent Learning

This review examines coordination and robustness in multi-agent learning. The organizing question is how learning agents can coordinate under partial observability, changing partners, communication limits, and strategic behaviour. Ten related scholarly sources are synthesized through a decision-centered framework spanning problem definition, mechanism, measurement, evaluation, implementation, and governance. The review does not invent experiments, pooled estimates, or unreported quantitative results. It instead evaluates the strength and transferability of the available evidence, with particular attention to reporting cooperative reward while concealing brittle conventions and unsafe equilibria. The resulting framework links technical or empirical performance to explicit use conditions and identifies tests that should precede wider adoption in multi-agent and distributed autonomous systems.

1. Chu, T., Wang, J., Codeca, L., & Li, Z. (2019). Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control. IEEE Transactions on Intelligent Transportation Systems, 21(3), 1086-1095. https://doi.org/10.1109/tits.2019.2901791 DOI
2. Gronauer, S., & Diepold, K. (2021). Multi-agent deep reinforcement learning: a survey. Artificial Intelligence Review, 55(2), 895-943. https://doi.org/10.1007/s10462-021-09996-w DOI
3. Liu, H., Zhang, C., Chai, Q., Meng, K., Guo, Q., & Dong, Z. Y. (2021). Robust Regional Coordination of Inverter-Based Volt/Var Control via Multi-Agent Deep Reinforcement Learning. IEEE Transactions on Smart Grid, 12(6), 5420-5433. https://doi.org/10.1109/tsg.2021.3104139 DOI
4. Omidshafiei, S., Pazis, J., Amato, C., How, J. P., & Vian, J. (2017). Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability. arXiv (Cornell University), 2681-2690. https://doi.org/10.48550/arxiv.1703.06182 DOI
5. Orr, J., & Dutta, A. (2023). Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey. Sensors, 23(7), 3625. https://doi.org/10.3390/s23073625 DOI
6. Silva, F. L. D., & Costa, A. H. R. (2019). A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems. Journal of Artificial Intelligence Research, 64, 645-703. https://doi.org/10.1613/jair.1.11396 DOI
7. Wen, G., Chen, C. L. P., Feng, J., & Zhou, N. (2017). Optimized Multi-Agent Formation Control Based on an Identifier–Actor–Critic Reinforcement Learning Algorithm. IEEE Transactions on Fuzzy Systems, 26(5), 2719-2731. https://doi.org/10.1109/tfuzz.2017.2787561 DOI
8. Zhang, K., Yang, Z., Liu, H., Zhang, T., & Başar, T. (2018). Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1802.08757 DOI
9. Zhu, C., Dastani, M., & Wang, S. (2024). A survey of multi-agent deep reinforcement learning with communication. Autonomous Agents and Multi-Agent Systems, 38(1). https://doi.org/10.1007/s10458-023-09633-6 DOI
10. Zhu, D., Yang, B., Liu, Y., Wang, Z., Ma, K., & Guan, X. (2022). Energy management based on multi-agent deep reinforcement learning for a multi-energy industrial park. Applied Energy, 311, 118636. https://doi.org/10.1016/j.apenergy.2022.118636 DOI