EUVIMEDEUVIMED entdecken
Crossref

Safe Multi-agent Reinforcement Learning with Natural Language Constraints

Ziyan Wang, Meng Fang, Tristan Tomilin, Fei Fang, Yali Du

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (44) · 38007-38015

DOI: 10.1609/aaai.v40i44.41138 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ziyan Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Safe Multi-Agent Reinforcement Learning (MARL) typically relies on manually specified numeric cost functions to ensure that policy behaviours respect safety constraints. As systems scale and human-defined constraints become more diverse, context-dependent, and frequently updated, hand-crafting such cost functions becomes prohibitively complex, tedious, and error-prone. Natural language offers an intuitive and flexible alternative for defining constraints, enabling broader accessibility and easier adaptation to new scenarios and evolving rules. However, current MARL frameworks lack effective mechanisms to incorporate free-form textual constraints in a robust and principled way. To bridge this gap, we introduce Safe Multi-Agent Reinforcement Learning with natural Language constraints (SMALL), a framework that leverages fine-tuned language models to parse and encode textual constraints into semantically meaningful embeddings. These embeddings characterise prohibited states or behaviours and enable automatic prediction of constraint violations. We integrate the resulting learned costs directly into MARL training, allowing agents to optimise task performance while simultaneously minimising constraint violations, without requiring manually engineered numeric cost functions. To rigorously evaluate our method, we also propose the LaMaSafe benchmark---a set of diverse multi-agent tasks designed to assess the capability of MARL algorithms to understand and adhere to realistic, human-provided natural language constraints. Experimental results across LaMaSafe environments show that SMALL achieves comparable task performance to strong MARL baselines while significantly reducing constraint violations. While SMALL does not provide formal safety guarantees, it demonstrates that natural language can be used to shape multi-agent behaviour toward safer policies.

Zitieren

APA

Wang, Z., Fang, M., Tomilin, T., Fang, F., & Du, Y. (2026). Safe Multi-agent Reinforcement Learning with Natural Language Constraints. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 38007-38015. https://doi.org/10.1609/aaai.v40i44.41138

Vancouver

Wang Z, Fang M, Tomilin T, Fang F, Du Y. Safe Multi-agent Reinforcement Learning with Natural Language Constraints. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(44):38007-38015. doi:10.1609/aaai.v40i44.41138

BibTeX
@article{Wang2026,
  author = {Wang, Ziyan and Fang, Meng and Tomilin, Tristan and Fang, Fei and Du, Yali},
  title = {Safe Multi-agent Reinforcement Learning with Natural Language Constraints},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {44},
  pages = {38007--38015},
  doi = {10.1609/aaai.v40i44.41138}
}
Kostenlos starten →