Adaptivity in agent-based routing for data networks

Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems MAS's in noisy environments. One important consideration in designing adaptive agents is choosing their action spaces to be as amenable as possible to machine learning techniques, especially to reinforcement learning RL techniques 22 . One important way to have the interaction structure connecting agents itself be adaptive is to have the intentions and or actions of the agents be in the input spaces of the other agents, much as in Stackelberg games 2, 16, 15, 18 . We consider both kinds of adaptivity in the design of a MAS to control network packet routing 21, 6, 17, 12 We demonstrate on the OPNET event-driven network simulator the perhaps surprising fact that simply changing the action space of the agents to be better suited to RL can result in very large improvements in their potential performance: at their best settings, our le...

• Type: Conference
• Year: 2000
• Where: AGENTS
• Authors: David Wolpert, Sergey Kirshner, Christopher J. Merz, Kagan Tumer
• Keywords: Adaptive Agents, AGENTS 2000, Interaction Structure, Security Privacy, Structure Connecting Agents