In this paper, we describe how certain aspects of the biological phenomena of stigmergy can be imported into multiagent reinforcement learning (MARL), with the purpose of better enabling coordination of agent actions and speeding up learning. In particular, we detail how these stigmergic aspects can be used to define an inter-agent communication framework.
Citation:
Raghav Aras, Alain Dutech, Fran?ois Charpillet, "Stigmergy in Multi Agent Reinforcement Learning," his, pp.468-469, Fourth International Conference on Hybrid Intelligent Systems (HIS'04), 2004