Reinforcement Learning (RL) and its integration with deep learning have achieved impressive performance in various robotic control tasks, ranging from motion planning and navigation to end-to-end visual manipulation. However, stability is not guaranteed in model-free RL by solely using data. From a control-theoretic perspective, stability is the most important property for any control system, since it is closely related to safety, robustness, and reliability of robotic systems. In this letter, we propose an actor-critic RL framework for control which can guarantee closed-loop stability by employing the classic Lyapunov's method in control theory. First of all, a data-based stability theorem is proposed for stochastic nonlinear systems modeled by Markov decision process. Then we show that the stability condition could be exploited as the critic in the actor-critic RL to learn a controller/policy. At last, the effectiveness of our approach is evaluated on several well-known 3-dimensional robot control tasks and a synthetic biology gene network tracking task in three different popular physics simulation platforms. As an empirical evaluation on the advantage of stability, we show that the learned policies can enable the systems to recover to the equilibrium or way-points when interfered by uncertainties such as system parametric variations and external disturbances to a certain extent.


    Access

    Download


    Export, share and cite



    Title :

    Actor-Critic Reinforcement Learning for Control With Stability Guarantee


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

    Publication date :

    2020-10-01


    Remarks:

    IEEE Robotics and Automation Letters , 5 (4) pp. 6217-6224. (2020)


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629





    Soft Actor-Critic Deep Reinforcement Learning for Fault Tolerant Flight Control

    Dally, Killian / Kampen, Erik-Jan Van | TIBKAT | 2022


    Actor-Critic Traction Control Based on Reinforcement Learning with Open-Loop Training

    Funk Drechsler, Maikol / Fiorentin, Thiago Antonio / Göllinger, Harald | BASE | 2022

    Free access

    Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic

    Ren, Yangang / Duan, Jingliang / Li, Shengbo Eben et al. | IEEE | 2020