GrDHP: A General Utility Function Representation for Dual Heuristic Dynamic Programming

著录项

• 来源
  《Neural Networks and Learning Systems, IEEE Transactions on》 |2015年第3期|614-627|共14页
• 作者

  Ni Z.; He H.; Zhao D.; Xu X.; Prokhorov D.V.;

  展开▼
• 作者单位

  Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI, USA;

  展开▼
• 收录信息
• 原文格式 PDF
• 正文语种 eng
• 中图分类
• 关键词

  Approximation methods; Density estimation robust algorithm; Dynamic programming; Learning systems; Neural networks; Nickel; Power system dynamics; Adaptive control; adaptive dynamic programming (ADP); dual heuristic dynamic programming (DHP); general utility function; goal representation; reinforcement learning (RL); reinforcement learning (RL).;

  机译：近似方法;密度估计鲁棒算法;动态规划;学习系统;神经网络;镍;电力系统动力学;自适应控制;自适应动态规划（ADP）;双重启发式动态规划（DHP）;通用效用函数;目标表示;强化学习（RL）;强化学习（RL）。;