The first Trading Agent Competition (TAC) was held from June 22nd to July 8th, 2000, organized by a group of researchers and developers led by Michael Wellman of the University of Michigan and Peter Wurman of North Carolina State University [Wellman, Wurman, O'Malley, Bangera, Lin, Reeves, WalshWellman et al.2001]. Their goals included providing a benchmark problem in the complex and rapidly advancing domain of e-marketplaces [EisenbergEisenberg2000] and motivating researchers to apply unique approaches to a common task. A key feature of TAC is that it required autonomous bidding agents to buy and sell multiple interacting goods in auctions of different types.
Another key feature of TAC was that participating agents competed against each other in a preliminary round and many practice games leading up to the finals. Thus, developers changed strategies in response to each others' agents in a sort of escalating arms race. Leading into the competition day, a wide variety of scenarios were possible. A successful agent needed to be able to perform well in any of these possible circumstances.
This article describes ATTac-2000, the first-place finisher in TAC. ATTac-2000 uses a principled bidding strategy, which includes several elements of adaptivity. In addition to the success at the competition, isolated empirical results are presented indicating the robustness and effectiveness of ATTac-2000's adaptive strategy.
The remainder of the article is organized as follows. Section 2 presents the details of the TAC domain. Section 3 introduces ATTac-2000, including the mechanisms behind its adaptivity. Section 4 describes the competition results and the results of controlled experiments testing ATTac-2000's adaptive components. Section 5 compares ATTac-2000 with some of the other TAC participants. Section 6 presents possible directions for future research and concludes.