KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning

Computer Science > Artificial Intelligence [Submitted on 8 Apr 2026] KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning Monirul Islam Pavel, Siyi Hu, Muhammad Anwar Masum, Mahardhika Pratama, Ryszard Kowalczyk, Zehong Jimmy Cao Real world deployment of multi agent reinforcement learning MARL systems is fundamentally constrained by limited compute memory and inference time. While expert policies achieve high performance they rely on costly decision cycles and large scale models that are impractical for edge devices or embedded platforms. Knowledge distillation KD offers a promising path toward resource aware execution but existing KD methods in MARL focus narrowly on action imitation often neglecting coordination structure and assuming uniform agent capabilities. We propose resource aware Knowledge Distillation for Multi Agent Reinforcement Learning KD MARL a two stage framework that transfers coordinated behavior from a centralized expert to lightweight decentralized student agents. The student policies are trained without a critic relying instead on distilled advantage signals and structured policy supervision to preserve coordination under heterogeneous and limited observations. Our approach transfers both action level behavior and structural coordination patterns from expert policies while supporting heterogeneous student architectures allowing each agent model capacity to match its observation complexity which is crucial for efficient execution under partial or limited observability and limited onboard resources. Extensive experiments on SMAC and MPE benchmarks demonstrate that KD MARL achieves high performance retention while substantially reducing computational cost. Across standard multi agent benchmarks KD MARL retains over 90 percent of expert performance while reducing computational cost by up to 28.6 times FLOPs. The proposed approach achieves expert level coordination and preserves it through structured distillation enabling practical MARL deployment across resource constrained onboard platforms. Comments: Accepted in IJCNN 2026 Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.06691 [cs.AI]   (or arXiv:2604.06691v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.06691 Focus to learn more Submission history From: Monirul Islam Pavel [view email] [v1] Wed, 8 Apr 2026 05:12:40 UTC (2,564 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)