Learning Attentional Communication with a Common Network for Multiagent Reinforcement Learning.

Journal: Computational intelligence and neuroscience
PMID:

Abstract

For multiagent communication and cooperation tasks in partially observable environments, most of the existing works only use the information contained in hidden layers of a network at the current moment, limiting the source of information. In this paper, we propose a novel algorithm named multiagent attentional communication with the common network (MAACCN), which adds a consensus information module to expand the source of communication information. We regard the best-performing overall network in the historical moment for agents as the common network, and we extract consensus knowledge by leveraging such a network. Especially, we combine current observation information with the consensus knowledge to infer more effective information as input for decision-making through the attention mechanism. Experiments conducted on the StarCraft multiagent challenge (SMAC) demonstrate the effectiveness of MAACCN in comparison to a set of baselines and also reveal that MAACCN can improve performance by more than 20% in a super hard scenario especially.

Authors

  • Wenwu Yu
    Department of Mathematics, Southeast University, Nanjing 210096, China; Faculty of Engineering, King Abdulaziz University, Jeddah 21589, Saudi Arabia.
  • Rui Wang
    Department of Clinical Laboratory Medicine Center, Inner Mongolia Autonomous Region People's Hospital, Hohhot, Inner Mongolia, China.
  • Xiaohui Hu
    School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China.