Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards

arXiv:2402.09075v1 Announce Type: cross
Abstract: The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of steady-state error often manifest when quadratic reward functions are employed. Although existing solutions using absolute-value-type reward functions partially address this problem, they tend to induce substantial fluctuations in specific system states, leading to abrupt changes. In response to this challenge, this study proposes an approach that introduces an integral term. By integrating …

abstract arxiv attention compensation cs.lg cs.sy eess.sy error function functions impact manifest performance reinforcement reinforcement learning solutions state type value