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 2301.01667eess.SYcs.LGcs.SY
收藏

基于强化学习的大数据学习MPC

Learning-based MPC from Big Data Using Reinforcement Learning

Norwegian University of Science and Technology (NTNU)(挪威科技大学)

Shambhuraj Sawant, Akhil S Anand, Dirk Reinhardt, Sebastien Gros

摘要:

提出了一种利用强化学习方法直接从数据中学习模型预测控制(MPC)方案的方法。最先进的学习方法使用RL来提高参数化MPC方案的性能。然而,这些学习算法通常是基于梯度的方法,需要频繁评估计算昂贵的MPC方案,从而限制了它们在大数据集上的使用。我们建议通过使用RL的工具来解决这个问题,以离线方式直接从数据中学习参数化MPC方案。我们的方法推导出MPC方案,而不必在收集的数据集上求解它,从而消除了现有大数据技术的计算复杂性。我们评估所提出的方法不同的复杂性的三个模拟实验。

英文摘要:

This paper presents an approach for learning Model Predictive Control (MPC) schemes directly from data using Reinforcement Learning (RL) methods. The state-of-the-art learning methods use RL to improve the performance of parameterized MPC schemes. However, these learning algorithms are often gradient-based methods that require frequent evaluations of computationally expensive MPC schemes, thereby restricting their use on big datasets. We propose to tackle this issue by using tools from RL to learn a parameterized MPC scheme directly from data in an offline fashion. Our approach derives an MPC scheme without having to solve it over the collected dataset, thereby eliminating the computational complexity of existing techniques for big data. We evaluate the proposed method on three simulated experiments of varying complexity.

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。

↑