Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control
Abstract
High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These issues are exacerbated when the task requires the agent to achieve a precise goal state, as is common in robotics and other real-world applications.We introduce Adviser-Actor-Critic (AAC), designed to address the precision control dilemma by combining the precision of feedback control theory with the adaptive learning capability of RL and featuring an Adviser that mentors the actor to refine control actions, thereby enhancing the precision of goal attainment.Finally, through benchmark tests, AAC outperformed standard RL algorithms in precision-critical, goal-conditioned tasks, demonstrating AAC's high precision, reliability, and robustness.Code are available at: https://anonymous.4open.science/r/Adviser-Actor-Critic-8AC5.
Cite
@article{arxiv.2502.02265,
title = {Adviser-Actor-Critic: Eliminating Steady-State Error in Reinforcement Learning Control},
author = {Donghe Chen and Yubin Peng and Tengjie Zheng and Han Wang and Chaoran Qu and Lin Cheng},
journal= {arXiv preprint arXiv:2502.02265},
year = {2025}
}
Comments
13 pages, 9 figures