Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time Systems
This addresses stabilization problems for uncertain real systems, but it is incremental as it builds on existing deep Q-learning methods with simulator integration.
The paper tackles the challenge of applying reinforcement learning to stabilize uncertain discrete-time systems by proposing a two-stage algorithm that uses multiple virtual simulators to pre-train Q-functions and then adapts them online to the real system, showing usefulness in numerical simulations.
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.