Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time Systems

TL;DR

This paper introduces a two-stage reinforcement learning method using simulators with multiple system models to stabilize uncertain discrete-time systems, improving learning efficiency and robustness.

Contribution

The proposed approach combines multiple virtual system models with continuous deep Q-learning to enhance policy stability under model uncertainties.

Findings

Effective stabilization demonstrated in numerical simulations.

Improved learning efficiency over traditional RL methods.

Robustness against identification errors in system parameters.

Abstract

Applications of reinforcement learning (RL) to stabilization problems of real systems are restricted since an agent needs many experiences to learn an optimal policy and may determine dangerous actions during its exploration. If we know a mathematical model of a real system, a simulator is useful because it predicates behaviors of the real system using the mathematical model with a given system parameter vector. We can collect many experiences more efficiently than interactions with the real system. However, it is difficult to identify the system parameter vector accurately. If we have an identification error, experiences obtained by the simulator may degrade the performance of the learned policy. Thus, we propose a practical RL algorithm that consists of two stages. At the first stage, we choose multiple system parameter vectors. Then, we have a mathematical model for each system parameter vector, which is called a virtual system. We obtain optimal Q-functions for multiple virtual systems using the continuous deep Q-learning algorithm. At the second stage, we represent a Q-function for the real system by a linear approximated function whose basis functions are optimal Q-functions learned at the first stage. The agent learns the Q-function through interactions with the real system online. By numerical simulations, we show the usefulness of our proposed method.