Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management
A hybrid offline-online multi-agent reinforcement learning framework based on decision transformers that incorporates return-weighted sampling, a critic conditioned on neighbors' actions, and neighborhood-correlated exploration that achieves quality-of-service (QoS) performance comparable to centralized methods.
Yi-Ming Zhang, Kun Yang, Cong Shen et al.
· 0 citations