Advances in Memetic Automaton: Toward Human-Like Autonomous Agents in Complex Multi-Agent Learning Problems
Yaqing Hou, Xiangchao Yu, Yifeng Zeng, Ziqi Wei, Haijun Zhang, Hongwei Ge, Qiang Zhang · IEEE Computational Intelligence Magazine · 2021
The meme-centric memetic automaton (MA) was recently proposed as an adaptive entity or a software agent wherein memes are defined as the building blocks of knowledge. The conceptualization of MA has led to the development of a large number of potentially rich meme-inspired designs that form a cornerstone of memetic computation as tools for problem-solving. In this study, we investigate the use of memetic multi-agent systems to develop more intelligent and human-like autonomous agents by taking MA as the essential backbone of the agent. Taking inspiration from a psychological Broadbent-Treisman Attenuation Model, we propose an attention intensity control method inmeme expressionfor enhancing agents’ perception of thevalueof all kinds of information captured from the environment, hence leading to a greater capability of meme knowledge generalization. Our particular focus is placed on the design ofmeme selectionfor more effective knowledge transmission across the population. To this end, we introduce a bidirectional imitation strategy based on agents’ estimation of the importance and/or uncertainty of decision making in a dynamic environment. Experiments on a minefield navigation simulation as well as a commercial video game demonstrate the superior performance of our proposed method compared to state-of-the-art methods.