蔡 军,苟文耀,刘 颜.基于 actor-critic 框架的在线积分强化学习算法研究[J].电子测量与仪器学报,2023,37(3):194-201 |
基于 actor-critic 框架的在线积分强化学习算法研究 |
Research on online integral reinforcement learning algorithm based on actor-critic framework |
|
DOI: |
中文关键词: 积分强化学习 RBF 神经网络 非线性仿射系统 跟踪控制 |
英文关键词:integral reinforcement learning RBF neural network nonlinear affine system tracking control |
基金项目:重庆市教委科学技术研究项目(KJZD-M202200603)、重庆市自然科学基金项目(CSTB2022NSCQ-MSX0380)资助 |
|
|
摘要点击次数: 605 |
全文下载次数: 936 |
中文摘要: |
针对轮式移动机器人动力学系统难以实现无模型的最优跟踪控制问题,提出了一种基于 actor-critic 框架的在线积分强
化学习控制算法。 首先,构建 RBF 评价神经网络并基于近似贝尔曼误差设计该网络的权值更新律,以拟合二次型跟踪控制性
能指标函数。 其次,构建 RBF 行为神经网络并以最小化性能指标函数为目标设计权值更新律,补偿动力学系统中的未知项。
最后,通过 Lyapunov 理论证明了所提出的积分强化学习控制算法可以使得价值函数,行为神经网络权值误差与评价神经网络
权值误差一致最终有界。 仿真和实验结果表明,该算法不仅可以实现对恒定速度以及时变速度的跟踪,还可以在嵌入式平台上
进行实现。 |
英文摘要: |
For the problem that it is difficult to achieve model-free optimal tracking control in the dynamic system of wheeled mobile
robot, a new online integral reinforcement learning control algorithm based on actor-critic framework is proposed in this paper. Firstly,
the critic neural network based on RBF is constructed to fit the quadratic tracking control performance index function and the weight
updating law of the network is designed based on the approximate Behrman error. Secondly, the RBF actor neural network is constructed
to compensate the unknown terms in the dynamic system and the weight updating law is designed to minimize the performance index
function. Finally, it is proved by Lyapunov theory that the proposed integral reinforcement learning control algorithm can make the value
function, the critic and actor neural network weights error uniformly and finally bounded. Simulation and experimental results show that
the algorithm not only realizes the tracking of constant or time-varying velocity, but also can be implemented on the embedded platform. |
查看全文 查看/发表评论 下载PDF阅读器 |