FedFormer: Contextual Federation with Attention in Reinforcement Learning. (arXiv:2205.13697v1 [cs.LG])

A core issue in federated reinforcement learning is defining how to aggregate
insights from multiple agents into one. This is commonly done by taking the
average of each participating agent's model weights into one common model
(FedAvg). We instead propose FedFormer, a novel federation strategy that
utilizes Transformer Attention to contextually aggregate embeddings from models
originating from different learner agents. In so doing, we attentively weigh
contributions of other agents with respect to the current agent's environment
and learned relationships, …

arxiv attention federation learning reinforcement reinforcement learning