In agent-based markets, adapting to the behavior of other agents is often necessary for success. When it is not possible to directly model individual competitors, an agent may instead model and adapt to the market conditions that result from competitor behavior. Such an agent could still benefit from reasoning about specific competitor strategies by considering how various combinations of these strategies would impact the conditions being modeled. We present an application of such an approach to a specific prediction problem faced by the agent TacTex in the Trading Agent Competition's Supply Chain Management scenario (TAC SCM).

PDF, PS, HTML

In AAMAS 2007 Workshop on Agent Mediated Electronic Commerce, 2007.

@inproceedings{amec07-tactex, title={Adapting Price Predictions in TAC SCM}, author={David Pardoe and Peter Stone}, booktitle={AAMAS 2007 Workshop on Agent Mediated Electronic Commerce}, url="http://www.cs.utexas.edu/users/ai-lab/?amec07-tactex", year={2007} }