期刊文献+

一种基于个性的作战实体行为模型构建框架及方法

A Personality-Based Combat Behavior Modeling Architecture and Methods
在线阅读 下载PDF
导出
摘要 作战实体建模面对作战中多样性和行为特点的互异性,需要刻画的行为变量众多、关系复杂,本文提出一种基于个性的作战实体行为建模方法,建立个性驱动行为生成概念框架,建立个性的表达、个性驱动的行动选择、个性的优化等子模型,并运用于指挥训练系统,为受训指挥员和机关人员构建形神兼备、公正逼真的模拟作战实体,较好地提升了训练效果。 Combat entity modeling should face the problem of expressing behaviors with uncountable va-riables and relations under the complex combat environment, which has the characteristic of di-versity and heterogeneity. In this paper, firstly, a personality-driven behavior generation concept framework is constructed, then a personality-based combat behavior modeling method is proposed, which composed of personality expressing model, personality based behavior choosing model, personality optimizing model. As a result, it promotes the reliability and variety of behavior models, and can be used for command training system to acquire better training effect.
出处 《人工智能与机器人研究》 2019年第4期248-254,共7页 Artificial Intelligence and Robotics Research
基金 国家自然科学基金71401177资助。
  • 相关文献

参考文献4

二级参考文献35

  • 1林民旺.前景理论与外交决策[J].外交评论(外交学院学报),2006,23(5):62-68. 被引量:41
  • 2Andrew Ilachinski. Land Warfare and Complexity. PartI_: Mathematical Background and Technical Sourcebook[DB/OL].Center for Naval Analyses, 199612009-03-10]. http://www.cna.org.
  • 3Bellman R. E. Dynamic Programming[M].Princeton University Press, 1957.
  • 4Sutton R. s. Learning to predict by the method of temporal difference[J].Maehine Learning, 1988,3(1):9-44.
  • 5Watkins C, Dayan-P. Q-learning[J].Machine Learning, 1992,8(3):279-292.
  • 6Watkins C. Leaming from delayed rewards[D]. England: King's College, University of Cambridge, 1989.
  • 7Grefenstette J. Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms[J] .Machine Learning, 1988(3):225-245.
  • 8Miyazaki, K, Kobayashi S. On the rationality of profit sharing in multi-agent reinforcement leaming[C].Fourth International Conference on Computational Intelligence and Multimedia Applications Proceedings,2001:421-425.
  • 9Whitehead S.D, Ballad D.H. Active perception and Reinforcement Learning[C]. Proceedings of the 7th International Conference on Machine Learning, 1990:162-169.
  • 10Sen. S., Saharan M. teal. Adaptation and Learning in Multi-agent systems[M].Berlin Heidelberg: Spring Verlag, 1995:218-233.

共引文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部