Reward Planning for Underactuated Robotic Systems: A Study on Pendubot with Parameters Uncertainty

There is a burgeoning interest in the field of Reinforcement Learning (RL) across various domains, including robotics. Traditional control approaches for robotic systems, such as semi-definite programming (SDP) or mixed integer programming (MIP), typically rely on the assumption of a known and deterministic model of the environment. In contrast, this study aims to introduce a novel RL method for planning the reward function specifically tailored for underactuated robotic systems with parameter uncertainty. We propose a method with a single RL agent to address the challenge of swing up and balance of a Pendubot system with uncertain parameters. The ultimate objective is to enhance the system’s ability to adapt and perform reliably in the face of varying uncertainties.