Learning and Stabilisation of Altruistic Behaviours in Multi-agent Systems by Reciprocity.

Optimisation of performance in collective systems often requires altruism. Emergence and stabilisation of altruistic behaviours are difficult because the agents incur a cost when behaving altruistically. In this paper we propose a biologically inspired strategy to learn stable alttruistic behaviours in artificial multi-agent systems, namely reciprocal altuism.This strategy in conjunction with learning capabilities make altruistic agents cooperate only between them, thus preventing their exploitation by selfish agents, if future benefits are greater than the current cost of altruistic acts. Our multi-agent system is made up of agents with a behaviour- based architecture. Agents learn the most suitable cooperative strategy for different environments by means of a reinforcement learning algorithm. Each agent receives a reinforcement signal that only measures its individual performance. Simulation results show how the multi-agent system learn stable altruistic behaviours, so reaching optimal performances in unknown and changing environments.

ZAMORA Javier;  MURCIANO Antonio; 

1998-03-03

JRC15909

https://publications.jrc.ec.europa.eu/repository/handle/JRC15909,