Emergent agent communication in multi-agent systems using automatically defined function genetic programming (ADF-GP)

Multi-agent systems, in which independent software agents interact with each other to achieve common goals, complete concurrent distributed tasks under autonomous control. In this paper we propose a method applying automatically defined function genetic programming (ADF-GP) to allow agents to autonomously learn effective agent communication messaging in order to achieve group behavior. A software simulation of a multi-agent system was used to observe the effectiveness of the proposed method. Using the proposed method, emergence of a compact and efficient agent communication protocol for the multi-agent system was observed.

[1]  Lee Spector,et al.  Cultural transmission of information in genetic programming , 1996 .

[2]  John R. Koza,et al.  Scalable learning in genetic programming using automatic function definition , 1994 .

[3]  Lee Spector,et al.  Evolving teamwork and coordination with genetic programming , 1996 .

[4]  Hitoshi Iba,et al.  Evolving communicating agents based on genetic programming , 1997, Proceedings of 1997 IEEE International Conference on Evolutionary Computation (ICEC '97).

[5]  Susan E. Conry,et al.  Fine-grained multiagent systems for the Internet , 1998, Proceedings International Conference on Multi Agent Systems (Cat. No.98EX160).