.png){kind=icon}
返回
Evolving neuro-controllers for a dynamic system using Structured Genetic Algorithms
.png){kind=icon}
PRE
AI
DOI：10.1023/A:1008291923124.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper describes the application of the Structured Genetic Algorithm (sGA) to design neurocontrollers for an unstable physical system. In particular, the approach uses a single unified genetic process to automatically evolve complete neural nets (both architectures and their weights) for controlling a simulated pole-cart system. Experimental results demonstrate the effectiveness of the sGA-evolved neuro-controllers for the task-to keep the pole upright (within specified vertical angle) and the cart within the limits of the given track.
Keyword:
genetic algorithms
neural networks
pole-cart system
neuro-controller
simulation
gene activation
multi-level chromosome
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
