Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914560512884736 |
|---|---|
| author | Amoh, Benjamin Parker, Geoffrey Marrero, Wesley |
| author_facet | Amoh, Benjamin Parker, Geoffrey Marrero, Wesley |
| contents | 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 \textbf{SeqComm-DFL}, unifying the sequential communication with decision-focused learning for task performance. Our approach features \emph{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 \emph{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 $\mathcal{O}(1/\sqrt{T})$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08944 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication Amoh, Benjamin Parker, Geoffrey Marrero, Wesley Machine Learning Multiagent Systems 68T05, 90C15, 68W15 I.2.6; I.2.11; F.2.2 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 \textbf{SeqComm-DFL}, unifying the sequential communication with decision-focused learning for task performance. Our approach features \emph{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 \emph{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 $\mathcal{O}(1/\sqrt{T})$ 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. |
| title | Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication |
| topic | Machine Learning Multiagent Systems 68T05, 90C15, 68W15 I.2.6; I.2.11; F.2.2 |
| url | https://arxiv.org/abs/2604.08944 |