arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.14992math.OC
收藏

随机离散时间系统 ${H_{2}/H_{\infty}}$ 控制的无模型强化学习

Model-free Reinforcement Learning for ${H_{2}/H_{\infty}}$ Control of Stochastic Discrete-time Systems

Xiushan Jiang, Li Wang, Dongya Zhao, Ling Shi

AI总结:

本文针对参数未知的随机离散时间系统,提出一种无需广义代数黎卡提方程的强化学习算法,以求解无限时间域 H2/H∞ 控制问题,并验证了其在 F-16 飞机自动驾驶仪等场景下的有效性与收敛性。

摘要:

本文针对一类随机离散时间系统,提出了一种用于无限时间域 $\rm {H_{2}/H_{\infty}}$ 问题的强化学习(RL)算法,而非使用一组耦合的广义代数黎卡提方程(GAREs)。即使系统参数未知,该算法也能学习系统的最优控制策略。此外,本文探讨了检测噪声的影响及算法的收敛性,并证明控制策略在有限次迭代后是可容许的。该算法还能处理随机领域内的多目标控制问题。最后,将该算法应用于带乘性噪声的 F-16 飞机自动驾驶仪。

英文摘要:

This paper proposes a reinforcement learning (RL) algorithm for infinite horizon $\rm {H_{2}/H_{\infty}}$ problem in a class of stochastic discrete-time systems, rather than using a set of coupled generalized algebraic Riccati equations (GAREs). The algorithm is able to learn the optimal control policy for the system even when its parameters are unknown. Additionally, the paper explores the effect of detection noise as well as the convergence of the algorithm, and shows that the control policy is admissible after a finite number of iterations. The algorithm is also able to handle multi-objective control problems within stochastic fields. Finally, the algorithm is applied to the F-16 aircraft autopilot with multiplicative noise.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑