Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication

arXiv:2604.08944v1 Announce Type: new Abstract: Multi-agent coordination under partial observability requires agents to share complementary private information. While recent methods optimize messages for intermediate objectives (e.g., reconstruction accuracy or mutual information), rather than decision quality, we introduce extbf{SeqComm-DFL}, unifying the sequential communication with decision-focused learning for task performance. Our approach features value-aware message generation with sequential Stackelberg conditioning: messages maximize receiver decision quality and are generated in priority order, with agents conditioning on their predecessors. The guidance potential determined by their prosocial ordering. We extend Optimal Model Design to communication-augmented world models with QMIX factorization, enabling efficient end-to-end training via implicit differentiation. We prove information-theoretic bounds showing that communication value scales with coordination gaps and establish O(1/sqrt{T}) convergence for the bilevel optimization, where T denotes the number of training iterations. On collaborative healthcare and StarCraft Multi-Agent Challenge (SMAC) benchmarks, SeqComm-DFL achieves four to six times higher cumulative rewards and over 13% win rate improvements, enabling coordination strategies inaccessible under information asymmetry.

Related

• Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning
• Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
• Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning
• Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning
• Multi-agent Adaptive Mechanism Design

Source: arXiv cs.LG | 2026-04-13