In the AdX game each competitor implements a software agent that performs the bidding strategy of an Ad Network (AdNet), while a game server simulates the behaviour of users, web sites, advertisers, and an Ad Exchange.

The trading agents by the students will compete to achieve the highest profit by implementing machine learning and other algorithms to best model the environment (e.g. users and competing agents) and optimize related actions and decisions (e.g. bids on advertising opportunities to users visiting publisher's web sites, bids on advertising campaigns and more). More details on the nature of the competition are available in the Ad-Exchange competition spec.