Learning to Communicate via Supervised Attentional Message Processing

Many tasks in AI require the collaboration of multiple agents. Generally, these agents cooperate with each other by message-passing communication. However, agents may suffer from being overwhelmed by massive received messages and have difficulties in obtaining useful information. To this end, we use an attention-based message processing (AMP) method to model agents' interactions by considering the relevance of each received message. To improve the efficiency of learning correct interactions, a supervised variant SAMP is then proposed to directly optimize the attentional weights in AMP with a target auxiliary interaction matrix from the environment. The empirical results demonstrate our proposal outperforms other competing multi-agent methods in "predator-prey-toxin" domain, and prove the superiority of SAMP in correctly guiding the optimization of attentional weights in AMP.