SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning
Overview & Synopsis
Multi-task generalization is an important yet underexplored problem in multi-agent reinforcement learning (MARL). Many real-world applications require multi-agent systems to generalize across complex, temporally extended tasks with diverse inter-agent coordination requirements. We introduce a specification language that combines temporal-logic task specifications with operators for expressing such requirements. We propose SpecMAGIC, a hierarchical framework that leverages the automaton structure of task specifications for subtask decomposition. A centralized high-level planner identifies and allocates compatible subtask sequences across agents, while decentralized low-level policies execute individual subtasks. This enables zero-shot generalization to new tasks by composing reusable subtask policies according to new specifications, without retraining. We establish soundness and probabilistic completeness of the high-level planner. Experiments on multi-agent navigation tasks show that SpecMAGIC substantially outperforms existing approaches on unseen task specifications and maintains strong performance as the number of agents increases.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning |
|---|---|
| Author / Organization | Zijian Guo, İlker Işık, H. M. Sabbir Ahmad, Wenchao Li |
| Subject & Discipline | cs.AI |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-266062 |
| Original Source Link | Visit Source Page on arxiv.org » |