Reinforcement learning (RL) is promising for complicated stochastic nonlinear control problems. Without using a mathematical model, an optimal controller can be learned from data evaluated by certain performance criteria through trial-and-error. However, the data-based learning approach is notorious for not guaranteeing stability, which is the most fundamental property for any control system. In this paper, the classic Lyapunov’s method is explored to analyze the uniformly ultimate boundedness stability (UUB) solely based on data without using a mathematical model. It is further shown how RL with UUB guarantee can be applied to control dynamic systems with safety constraints. Based on the theoretical results, both off-policy and on-policy learning algorithms are proposed respectively. As a result, optimal controllers can be learned to guarantee UUB of the closed-loop system both at convergence and during learning. The proposed algorithms are evaluated on a series of robotic continuous control tasks with safety constraints. In comparison with the existing RL algorithms, the proposed method can achieve superior performance in terms of maintaining safety. As a qualitative evaluation of stability, our method shows impressive resilience even in the presence of external disturbances.


    Access

    Download


    Export, share and cite



    Title :

    Reinforcement learning control of constrained dynamic systems with uniformly ultimate boundedness stability guarantee


    Contributors:
    Han, M (author) / Tian, Y (author) / Zhang, L (author) / Wang, J (author) / Pan, W (author)

    Publication date :

    2021-07-01


    Remarks:

    Automatica , 129 , Article 109689. (2021)


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Actor-Critic Reinforcement Learning for Control With Stability Guarantee

    Han, M / Zhang, L / Wang, J et al. | BASE | 2020

    Free access

    Ultimate Boundedness Theorem for Model Reference Adaptive Control Systems

    Hoecht, L. / Bierling, T. / Holzapfel, F. | AIAA | 2014



    Local stability and ultimate boundedness in the control of robot manipulators

    Arteaga Pérez, Marco Antonio / Gutiérrez-Giles, Alejandro / Pliego-Jiménez, Javier | TIBKAT | 2022