Reinforcement Learning‐Based Unicast and Broadcast Wireless Semantic Communications
Zhilin Lu, Rongpeng Li, Ekram Hossain, Zhifeng Zhao, Honggang Zhang · 2025
Semantic communication has been deemed as a promising communication paradigm to break through the bottleneck of traditional communications. Nonetheless, most of the existing works focus more on point-to-point communication scenarios and its extension to multiuser scenarios is not that straightforward due to its cost inefficiencies to directly scale the joint source-channel coding framework to the multiuser communication system. Meanwhile, previous methods optimize the system by differentiable bit-level supervision, easily leading to a “semantic gap.” Therefore, we delve into multiuser broadcast communication (BC) based on the universal transformer (UT) and propose a reinforcement learning (RL)-based self-critical alternate learning (SCAL) algorithm, named SemanticBC-SCAL, to capably adapt to the different BC channels from one transmitter (TX) to multiple receivers (RXs) for sentence generation task. Since the unicast scenario is a special case of the broadcast scenario, we have unified these two situations within the broadcast model. In particular, to enable stable optimization via a nondifferentiable semantic metric, we regard sentence similarity as a reward and formulate this learning process as an RL problem. Considering the huge decision space, we adopt a lightweight but efficient self-critical supervision to guide the learning process. Meanwhile, an alternate learning mechanism is developed to provide cost-effective learning, in which the encoder and decoders are updated asynchronously with different iterations. Notably, the incorporation of RL makes SemanticBC-SCAL compliant with any user-defined semantic similarity metric and simultaneously addresses the channel's nondifferentiability issue by alternate learning. Additionally, we also compare the performance in one-to-one scenarios built on the long short-term memory and UT architectures. Extensive simulation results are conducted to verify the effectiveness and superiorness of our approach in both unicast and broadcast scenarios.