Learning to Locate Trading Partners in Agent Networks

This paper is motivated by some recent, intriguing research results involving agent-organized networks (AONs). In AONs, nodes represent agents, and collaboration between nodes are represented by corresponding edges. Agents rewire edges, i.e., change partners, to improve performance. The challenge in these domains is the search and location of desirable interaction or collaboration partners in a relatively large population. It was found that random selection of partners in each time period produced better performance but incurred larger search costs in a production and exchange economy compared to gradual rewiring of edges in the network. We propose an exponentially decaying exploration scheme that produces similar utilities to random rewiring but with much less rewiring costs. We evaluate the effects of the number of trading partners on connections on the utilities obtained by the agents. We hypothesize on the cause for the observed performance differences and verify that by showing t...

• Type: Journal
• Year: 2009
• Where: ATAL
• Authors: John Porter, Kuheli Chakraborty, Sandip Sen
• Keywords: ATAL 2009, Intelligent Agents, Larger Search Costs, Observed Performance Differences, Rewiring