| 智能体对手建模研究进展 |
| |
| 作者姓名： | 刘婵娟 赵天昊 刘睿康 张 强 |
| |
| 作者单位： | 大连理工大学计算机科学与技术学院,辽宁 大连 116024 |
| |
| 基金项目： | 中国科协青年人才托举工程(2018QNRC001)；国家自然科学基金项目(61702075，31370778，61425002，61772100，61751203) |
| |
| 摘 要： | 智能体是人工智能领域的一个核心术语。近年来，智能体技术在自动无人驾驶、机器人系统、
电子商务、传感网络、智能游戏等方面得到了广泛研究与应用。随着系统复杂性的增加，关于智能体的研究重
心由对单个智能体的研究转变为智能体间交互的研究。多个智能体交互场景中，智能体对其他智能体决策行为
的推理能力是非常重要的一个方面，通常可以通过构建参与交互的其他智能体的模型，即对手建模来实现。对
手建模有助于对其他智能体的动作、目标、信念等进行推理、分析和预测，进而实现决策优化。为此，重点关
注智能体对手建模研究，展开介绍关于智能体动作预测、偏好预测、信念预测、类型预测等方面的对手建模
技术，对其中的优缺点进行讨论和分析，并对手建模技术当前面临的一些开放问题进行总结，探讨未来可能
的研究和发展方向。
|
| 关 键 词： | 决策智能 对手建模 博弈论 智能体系统 AlphaGo |
Research progress of opponent modeling for agent |
| |
| Authors: | LIU Chan-juan ZHAO Tian-hao LIU Rui-kang ZHANG Qiang |
| |
| Affiliation: | School of Computer Science and Technology, Dalian University of Technology, Dalian Liaoning 116024, China |
| |
| Abstract: | Agent is a core term in the field of artificial intelligence. In recent years, agent technology has been widely
studied and applied in such fields as autonomous driving, robot system, e-commerce, sensor network, and intelligent
games. With the increase of system complexity, the research focus on agent technology has been shifted from single
agent to interactions between agents. In scenarios with multiple interactive agents, an important direction is to reason
out other agents’ decisions and behaviors, which can be realized through the modeling of other agents involved in the
interaction, that is, opponent modeling. Opponent modeling is conducive to reasoning, analyzing, and predicting other
agents’ actions, targets, and beliefs, thus optimizing one’s decision-making. This paper mainly focused on the research
on opponent modeling of agents, and introduced the opponent modeling technology in agent action prediction,
preference prediction, belief prediction, and type prediction. In addition, their advantages and disadvantages were
discussed, some current open problems were summarized, and the possible future research directions were presented. |
| |
| Keywords: | decision intelligence opponent modeling game theory agent systems AlphaGo |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《》浏览原始摘要信息 |
|
点击此处可从《》下载全文 |
|
