federated reinforcement learning (FRL) has been deemed as a promising
solution for intelligent decision-making in the era of Artificial Internet of
Things. However, existing FRL approaches often entail repeated interactions
with the environment during local updating, which can be prohi
Federated Reinforcement Learning (FRL) algorithm, MFPO, enhances data utilization by controlling policy gradients using momentum and importance sampling, achieving efficient interaction and communication complexities with performance gains over existing methods.