Building a Believable and Effective Agent for a 3D Boxing Simulation Game
This paper describes an approach used to build and optimize a practical AI solution for a 3D boxing simulation game. The two main features of the designed AI agent are be lievability (human-likeness of agents behavior) and effective ness (agents capability to reach own goals). We show how learning by observation and case-based reasoning techniques are used to create believable behavior. Then we employ rein forcement learning to optimize agents behavior, turning the agent into a strong opponent, acting in a commercial-level game environment. The used knowledge representation scheme supports high maintainability, important for game developers.
believabitity behavior capture learning by observation reinforcement learning
Maxim Mozgovoy Iskander Umarov
University of Aizu Aizu-Wakamatsu, Japan TruSoft Intl Inc.St.Petersburg.Florida, USA
国际会议
成都
英文
14-18
2010-07-07（万方平台首次上网日期，不代表论文的发表时间）