Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee

by   Minghao Han, et al.

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.



There are no comments yet.


page 10


Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Deep Reinforcement Learning (DRL) has achieved impressive performance in...

Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles

Recently, barrier function-based safe reinforcement learning (RL) with t...

Automatic Policy Synthesis to Improve the Safety of Nonlinear Dynamical Systems

Learning controllers merely based on a performance metric has been prove...

Complete stability analysis of a heuristic ADP control design

This paper provides new stability results for Action-Dependent Heuristic...

A Reinforcement Learning-based Economic Model Predictive Control Framework for Autonomous Operation of Chemical Reactors

Economic model predictive control (EMPC) is a promising methodology for ...

Lyapunov-Regularized Reinforcement Learning for Power System Transient Stability

Transient stability of power systems is becoming increasingly important ...

Soft Q-network

When DQN is announced by deepmind in 2013, the whole world is surprised ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.