Abstract

Online auctions have become a popular method for business transactions. The variety of different auction rules, the restrictions in supply or demand, and the agents ’ com-binatorial preferences for the different commodities, have led to the creation of a very complex multi-agent “environment ” and a number of strategic tradeoffs. Designing an agent that deals efficiently with these tradeoffs has been a multi-pronged effort. Us-ing game-theoretic approaches, some equilibria have been computed for relatively sim-ple auctions. However, since these equilibria have limited practical application, due to the significant number of varying auctions that take place simultaneously, empiri-cal approaches and experimental evaluations of various strategies have also been used. Furthermore, progress has been made into designing better agent architectures. This dissertation presents results in all of these directions (theoretical and empiri-cal). We present a methodology for designing trading agents, and deciding their bidding strategy, when they participate in a large number of simultaneous auctions with a variety of rules. We use a modular, adaptive, scalable and robust agent architecture, combining principled methods and empirical knowledge. We decompose the problem faced by the

Citations