Metraipolis › archive › dc_2a6fe377fa56
Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management — arXiv:2608.28878
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28878
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:21.279Z
- SHA-256 of the archived text
9cb337238b0fda8b9f24c10c0a87ac3e578c102ded30a627c3428856dc035b56- Stable URL of this page
https://metraipolis.com/documento/dc_2a6fe377fa56
How to cite
Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management — arXiv:2608.28878 — arXiv (en), https://arxiv.org/abs/2608.28878 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a6fe377fa56 (Metraipolis archive dc_2a6fe377fa56, sha256 9cb337238b0fda8b9f24c10c0a87ac3e578c102ded30a627c3428856dc035b56)
BibTeX
@misc{dc2a6fe377fa56,
title = {Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management — arXiv:2608.28878},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28878},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a6fe377fa56; sha256 9cb337238b0fda8b9f24c10c0a87ac3e578c102ded30a627c3428856dc035b56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28878. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper develops a hybrid offline-online multi-agent reinforcement learning framework based on decision transformers. The policy is first pretrained offline via supervised sequence modeling of trajectories generated by existing policies, providing a safe and sample-efficient initialization. It is then fine-tuned online using a hybrid objective that incorporates critic-guided gradients, enabling performance improvements beyond the offline policy. To facilitate stable offline-to-online transfer and effective multi-agent coordination, the framework incorporates return-weighted sampling, a critic conditioned on neighbors' actions, and neighborhood-correlated exploration. The approach is fully distributed: both training and execution rely only on local observations and limited information exchange among neighboring agents. Evaluations with dynamic traffic arrivals in two settings: (i) joint scheduling and power allocation and (ii) coordinated beamforming, show that the proposed method achieves quality-of-service (QoS) performance comparable to centralized methods. Moreover, when pretrained on lower-quality datasets, online fine-tuning is also observed to surpass the initial offline policy. These results demonstrate a promising learning-based alternative for wireless resource management. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Systems and Control (eess.SY) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.28878 — 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 2026-10-17T07:28:26.698Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).