Reinforcement learning (RL) is a promising approach for deriving control policies for complex systems. As we show in two control problems, the derived policies from using the Proximal Policy Optimization (PPO) and Deep Q-Network (DQN) algorithms may lack robustness guarantees. Motivated by these issues, we propose a new hybrid algorithm, which we call Hysteresis-Based RL (HyRL), augmenting an existing RL algorithm with hysteresis switching and two stages of learning. We illustrate its properties in two examples for which PPO and DQN fail.
@article{arxiv.2204.00654,
title = {Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Control},
author = {Jan de Priester and Ricardo G. Sanfelice and Nathan van de Wouw},
journal= {arXiv preprint arXiv:2204.00654},
year = {2022}
}
Comments
This paper has been accepted for publication at the 2022 American Control Conference (ACC)