Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Abstract

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 paper, 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.

IEEE RA-L + IROS 2020

References in corpus (10)

• Continuous control with deep reinforcement learning
• Soft Actor-Critic Algorithms and Applications
• Dueling Network Architectures for Deep Reinforcement Learning
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• DeepMind Control Suite
• Neural Optimizer Search with Reinforcement Learning
• Lyapunov-based Safe Policy Optimization for Continuous Control
• A Lyapunov-based Approach to Safe Reinforcement Learning
• Finite-Sample Analysis for SARSA with Linear Function Approximation
• On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence

Cited by in corpus (3)

• Model-Reference Reinforcement Learning for Collision-Free Tracking Control of Autonomous Surface Vehicles
• Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee
• Battery Model Calibration with Deep Reinforcement Learning