Learning and stabilization of altruistic behaviors in multi-agent systems by reciprocity

Optimization of performance in collective systems often requires altruism. The emergence and stabilization of altruistic behaviors are dicult to achieve because the agents incur a cost when behaving altruistically. In this paper, we propose a biologically inspired strategy to learn stable altruistic behaviors in arti®cial multi-agent systems, namely reciprocal altruism. This strategy in conjunction with learning capabilities make altruistic agents cooperate only between themselves, thus preventing their exploitation by sel®sh agents, if future bene®ts are greater than the current cost of altruistic acts. Our multi-agent system is made up of agents with a behavior-based architecture. Agents learn the most suitable cooperative strategy for di€erent 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 learns stable altruistic behaviors,...

• Type: Journal
• Year: 1998
• Where: BC
• Authors: Javier Zamora, José del R. Millán, Antonio Murciano
• Keywords: Altruistic, Altruistic Behaviors, BC 1998, Multi-agent System