An empirical study of trading agent robustness

We study the empirical behavior of trading agents participating in the Ad-Auction game of the Trading Agent Competition (TAC-AA). Aiming to understand the applicability of optimal trading strategies in synthesized environments to real-life settings, we investigate the robustness of the agents to deviations from the game's specified environment. Our results indicate that most agents, especially the top-scoring ones, are surprisingly robust. In addition, using the game logs, we derive for each agent a strategic fingerprint and show that it almost uniquely identifies it. Finally, we show that although the Machine Learning modeling in TAC-AA is inherently inaccurate, further improvement in modeling accuracy is likely to have only a limited contribution to the overall performance of TAC-AA agents.