analiza aiqbench
This research advances wireless resource management by integrating offline pretraining with online fine-tuning within a distributed multi-agent reinforcement learning framework. By leveraging Decision Transformers to coordinate neighboring agents efficiently, the method achieves QoS performance comparable to centralized systems while adapting to dynamic traffic conditions. The approach offers a robust, sample-efficient alternative for optimizing joint scheduling and beamforming in complex network environments.
Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management
arXiv:2608.28878v1 Announce Type: cross Abstract: 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.
Abstract: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.
11 pages, 9 figures, 3 tables. Submitted to IEEE Journal on Selected Areas in Communications in Aug 2026. The offline training part was presented at the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Systems and Control (eess.SY); Artificial Intelligence (cs.AI)
arXiv:2608.28878 [eess.SY]
(or arXiv:2608.28878v1 [eess.SY] for this version)
https://doi.org/10.48550/arXiv.2608.28878 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 218 cuvinte
Subiecte conexe
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026
34 Amazon Research Awards Build on Trainium recipients announced
Amazon Science · 5 aug. 2026
Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking
arXiv · 16 iun. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026