首页> 外文会议>International Conference on Research in Intelligent and Computing in Engineering >Reinforcement Learning Based Adaptive Optimal Strategy in Robotic Control Systems
【24h】

Reinforcement Learning Based Adaptive Optimal Strategy in Robotic Control Systems

机译:基于机器人控制系统的加强学习自适应最优策略

获取原文

摘要

This paper considers the application of online adaptive dynamic programming for robotic systems including manipulators and wheeled inverted pendulum (WIP) systems. The sliding mode control technique enable us to implement the control design for reduced order systems and combine with Neural Networks. Both the two control problems are considered in main part of online adaptive reinforcement learning strategy. Finally, the theoretical analysis about the convergence of Actor/Critic as well as the tracking problem and simulation results demonstrate the effectiveness of the two proposed control schemes.
机译:本文考虑了用于机器人系统的在线自适应动态规划,包括操纵器和轮式倒立摆动系统(WIP)系统。 滑动模式控制技术使我们能够实现减少订单系统的控制设计,并与神经网络相结合。 两种控制问题都被认为是在线自适应加强学习策略的主要部分。 最后,关于演员/评论家的收敛性以及跟踪问题和仿真结果的理论分析表明了两个提出的控制方案的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号