Metraipolis › archive › dc_4178ae5526bc

Continual Graph Multi-Agent Reinforcement Learning — arXiv:2610.10302

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10302
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:16.304Z
SHA-256 of the archived text
84d2861860e60ef4e251d37653ae45b62f25f736ad22f858f86bdd9073453a56
Stable URL of this page
https://metraipolis.com/documento/dc_4178ae5526bc

How to cite

Continual Graph Multi-Agent Reinforcement Learning — arXiv:2610.10302 — arXiv (en), https://arxiv.org/abs/2610.10302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4178ae5526bc (Metraipolis archive dc_4178ae5526bc, sha256 84d2861860e60ef4e251d37653ae45b62f25f736ad22f858f86bdd9073453a56)
BibTeX
@misc{dc4178ae5526bc,
  title = {Continual Graph Multi-Agent Reinforcement Learning — arXiv:2610.10302},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10302},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4178ae5526bc; sha256 84d2861860e60ef4e251d37653ae45b62f25f736ad22f858f86bdd9073453a56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In Continual Multi-Agent Reinforcement Learning (CMARL), agents learn cooperative policies across sequences of tasks, aiming to adapt effectively to new tasks while preserving the ability to solve previously encountered ones. In many applications, tasks differ in their underlying structure, which can represent, for example, distinct operational conditions or target configurations (e.g., different network topologies in power grids or arrangements in formation control). Existing CMARL methods lack dedicated mechanisms to leverage this structural information when learning new tasks, failing to promote transfer and mitigate forgetting. To fill this gap, we propose Continual Graph Multi-Agent Reinforcement Learning (CGMARL), a novel framework for CMARL problems in which task sequences are mapped into a series of attributed graphs, each modeling a task-specific structure. In CGMARL, each graph determines the environment dynamics (next states and/or rewards) and the number of agents for the corresponding task. Then, we present Graph-based Formation (GRAFO), the first CGMARL benchmark, and show how forgetting arises in this setting. Finally, to address this limitation, we propose Frozen Graph Encoder (FROG), a method that relies on a frozen graph backbone to preserve past structural information in graph-based CMARL policies. Experiments on GRAFO show that pairing FROG with existing CL methods substantially improves performance on multiple CGMARL scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10302 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:14:15.326Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).