期刊文献+

一种用于机器人协同进化的级联模块式进化神经网络

A Cascade Module Type of Evolutionary Neural Network Used in the Robot Synergistic Evolution
下载PDF
导出
摘要 给出一种用于机器人协同进化的级联模块式进化神经网络,分析了其结构组成,提供了网络构造和进化方法,给出其评价。初步研究和仿真结果表明,该网络能够较好地满足开放社会机器人协同进化对速度和知识完备性的要求。 This paper introduces a cascade module type of evolutionary neural network used in the robot synergistic evolution and analyzes its structural elements.It also provides the network structure and evolutionary method,and gives its evaluation.The first study and simulation result show that this network can meet the requirements of speed and perfect knowledge for the synergistic evolution of the open social robots.
出处 《山东交通学院学报》 CAS 2002年第4期47-52,共6页 Journal of Shandong Jiaotong University
关键词 机器人 协同进化 级联模块式进化神经网络 体系结构 robot synergistic evolution a cascade module type of evolutionary neural network
  • 引文网络
  • 相关文献

参考文献7

二级参考文献20

  • 11.Dorigo M,Colombetti M. Robot shaping developing autonomous agents through learning. Artificial Intelligence,1994;71(2):321-370
  • 22.Steels L. Building agents with autonomous behavior systems. In:Steels LR Brooks.The `artificial life' route to `artificial intelli- gence',Building situated embodied agents,1994
  • 33.Dautenhahn K. Investigations into internal and external aspects of dynamic agent-environment couplings.in Proc. Dynamics,Syn-ergeticsAutonomous Agents Conference,March 2-5,Switzerland,Gstaad,1997
  • 44.Sutton R S. Temporal credit assignment in reinforcement lear- ning. Univ. Of Mass. Ph.D. dissertation.COINS TR 84-2Amherst,MA,1984
  • 55.Barto A G,Anandan P. Pattern recognizing stochastic learning automata. IEEE Trans.on Systemman and cybernetics,1985;15:360-375
  • 66.Angeline P. An evolutionary algorithm that constructs recurrent neural networks. IEEE Trans. on Neural Networks,1994;5(1):54-65
  • 77.Whitley D. Genetic reinforcement learning for neurocontrol pro- blems. Maching Learning,1993;13:259-284
  • 88.Ackley D,Littman D. Interaction between learning and evolu- tion. Artificial Life II,Addison Wesley1992
  • 99.Moriarty D Miikkulainen R. Efficient reinforcement learning through symbiotic evolution. Machine learning,1996;22:11-32
  • 1010.Gomez F,Miikkulainen R. Incremental Evolution of complex general behavior. Adaptive Behavior,1997;5(3/4):317-342

共引文献80

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