WhiteBear: An Empirical Study of Design Tradeoffs for Autonomous Trading Agents

Ioannis A. Vetsikas, and Bart Selman

This paper presents WhiteBear, one of the top-scoring agents in the 2 "'i International Trading Agent Competition (TAC). TAC was designed as a realistic complex test-bed for de-signing agents trading in e-marketplaces. Our architecture is an adaptive, robust agent architecture combining principled methods and empirical knowledge. The agent faced several technical challenges. Deciding the optimal quantities to buy and sell, the desired prices and the time of bid placement was only part of its design. Other important issues that we re-solved were balancing the aggressiveness of the agent’s bids against the cost of obtaining increased flexibility and the in-tegration of domain specific knowledge with general agent design techniques. We present our observations and back our conclusions with empirical results.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.