Agent Smith: a real-time game-playing agent for interactive dynamic games

The goal of this project is to develop an agent capable of learning and behaving autonomously and making decisions quickly in a dynamic environment. The agent’s environment is a fast-paced interactive game known as Unreal Tournament 2004. Unreal allows for a spectator to watch the agent as it performs its tasks and even to enter the game and challenge the agent. The agent’s behavior is controlled by a rule-based system, which looks at multiple high-level conditions, such as whether the agent is weak, and determines single high-level actions, such as whether to head for the nearest known healing source. Using an evolutionary computation approach, in which the behavior is evolved over a number of generations, the agent learns increasingly better strategies for its environment. Through the work in this project, we are exploring several research questions, including the development of successful vocabulary of high-level conditions and actions for the rule set, the challenges of rapid ...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Ryan K. Small
• Keywords: Agent’s Environment, GECCO 2008, Optimization, Rule Set, Rule-based System