2009 AIIDE Agent Modeling R. Zhao and D. Szafron, Learning Character Behaviors using Agent Modeling in Games, Proceedings of the Fifth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE), Stanford, USA, October, 2009, 179-185. abstract or pdf.
Abstract:

Our goal is to provide learning mechanisms to game agents so they are capable of adapting to new behaviors based on the actions of other agents. We introduce a new on-line reinforcement learning (RL) algorithm, ALeRT-AM, that includes an agent-modeling mechanism. We implemented this algorithm in BioWare Corp.ís role-playing game, Neverwinter Nights to evaluate its effectiveness in a real game. Our experiments compare agents who use ALeRTAM with agents that use the non-agent modeling ALeRT RL algorithm and two other non-RL algorithms. We show that an ALeRT-AM agent is able to rapidly learn a winning strategy against other agents in a combat scenario and to adapt to changes in the environment.