Proceedings

Context-Aware Multi-Agent Coordination: Learning Correlated Equilibria Under Situational Constraints

Libo Zhang, Zhirui Zeng, Yang Chen, Jiamou Liu

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 463-471.

https://doi.org/10.24963/ijcai.2026/53

Keywords

  • Agent-based and Multi-agent Systems: Multi-agent learning
  • Agent-based and Multi-agent Systems: Coordination and cooperation

Abstract

Effective multi-agent coordination requires aligning incentives while adhering to complex requirements. However, real-world systems often impose situational constraints, context-dependent requirements triggered only under specific conditions, which challenge standard Correlated Equilibria (CE) solutions. We propose Situational-Constrained Density-Based Correlated Equilibria (SC-DBCE), a novel concept in Markov Games that formalizes situational constraints as logic implications. To solve this, we introduce Situational-Constrained Correlated Policy Iteration (SC-CPI), a reinforcement learning algorithm employing a smooth Log-Sum-Exp mechanism for constraint optimization. Evaluations on multi-agent games, smart grids, and warehouse robotics demonstrate that SC-CPI consistently outperforms baselines in both equilibrium quality and constraint adherence. To our knowledge, this is the first method learning CE under situational constraints.

Libo Zhang, Zhirui Zeng, Yang Chen, and Jiamou Liu. 2026. Context-Aware Multi-Agent Coordination: Learning Correlated Equilibria Under Situational Constraints. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 463–471. https://doi.org/10.24963/ijcai.2026/53
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards