.png){kind=icon}
返回
Data-Driven Economic NMPC Using Reinforcement Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2019.2913768.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reinforcement learning (RL) is a powerful tool to perform data-driven optimal control without relying on a model of the system. However, RL struggles to provide hard guarantees on the behavior of the resulting control scheme. In contrast, nonlinear model predictive control (NMPC) and economic NMPC (ENMPC) are standard tools for the closed-loop optimal control of complex systems with constraints and limitations, and benefit from a rich theory to assess their closed-loop behavior. Unfortunately, the performance of (E)NMPC hinges on the quality of the model underlying the control scheme. In this paper, we show that an (E)NMPC scheme can be tuned to deliver the optimal policy of the real system even when using a wrong model. This result also holds for real systems having stochastic dynamics. This entails that ENMPC can be used as a new type of function approximator within RL. Furthermore, we investigate our results in the context of ENMPC and formally connect them to the concept of dissipativity, which is central for the ENMPC stability. Finally, we detail how these results can be used to deploy classic RL tools for tuning (E)NMPC schemes. We apply these tools on both, a classical linear MPC setting and a standard nonlinear example, from the ENMPC literature.
Keyword:
Optimal control
Adaptation models
Stochastic processes
Tools
Stability analysis
Economics
Reinforcement learning
Adaptive nonlinear model predictive control (NMPC)
economic NMPC (ENMPC)
reinforcement learning
strict dissipativity
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
分享收藏
Influence of chimpanzee predation on the red colobus population at Ngogo, Kibale National Park, Uganda.png)
Primates
PrimatesIF0
PREAI
分享收藏
查看更多内容