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 2403.04412math.OC
收藏

基于离策略强化学习的Itô随机系统无模型$H_{\text{∞}}$控制

Model-free $H_{\infty}$ control of Itô stochastic system via off-policy reinforcement learning

Jing Guo Jing Guo, Xiushan Jiang, Weihai Zhang

AI总结:

针对模型未知的线性随机Itô系统的$H_{\text{∞}}$控制问题,提出一种离策略强化学习方法直接从系统数据求解广义代数Riccati方程,证明了收敛性与鲁棒性,并在F-16飞机系统上验证了有效性。

摘要:

本文研究了系统模型未知的线性随机Itô系统的随机$H_{\text{∞}}$控制问题。已知线性随机$H_{\text{∞}}$控制问题可转化为求解所谓的广义代数Riccati方程(GARE)的问题,这是一种通常难以解析求解的非线性方程。更糟糕的是,当实际中无法获得准确的系统模型或构建模型成本过高时,基于模型的技术无法用于近似求解GARE。为解决这些问题,本文提出了一种离策略强化学习(RL)方法,可直接从实际系统数据而非系统模型中学习GARE的解;本文证明了该方法的收敛性,并研究了RL对学习过程中误差的鲁棒性。在该离策略RL方法中,系统数据可由行为策略而非目标策略生成,这一点在实际系统中具有重要意义和应用前景。最后,所提出的离策略RL方法在随机线性F-16飞机系统上得到了验证。

英文摘要:

The stochastic $H_{\infty}$ control is studied for a linear stochastic Itô system with an unknown system model. The linear stochastic $H_{\infty}$ control issue is known to be transformable into the problem of solving a so-called generalized algebraic Riccati equation (GARE), which is a nonlinear equation that is typically difficult to solve analytically. Worse, model-based techniques cannot be utilized to approximately solve a GARE when an accurate system model is unavailable or prohibitively expensive to construct in reality. To address these issues, an off-policy reinforcement learning (RL) approach is presented to learn the solution of a GARE from real system data rather than a system model; its convergence is demonstrated, and the robustness of RL to errors in the learning process is investigated. In the off-policy RL approach, the system data may be created with behavior policies rather than the target policies, which is highly significant and promising for use in actual systems. Finally, the proposed off-policy RL approach is validated on a stochastic linear F-16 aircraft system.

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。

↑