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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychen2025adviser

Related papers

• Recursive Least Squares Advantage Actor-critic Algorithms (2022)0.00
• Low-precision Reinforcement Learning: Running Soft Actor-critic In Half Precision (2021)0.00
• Ask-ac: An Initiative Advisor-in-the-loop Actor-critic Framework (2022)3.58
• Adaptively Calibrated Critic Estimates For Deep Reinforcement Learning (2021)7.16
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• Langevin Soft Actor-critic: Efficient Exploration Through Uncertainty-driven Critic Learning (2025)0.00
• Actor-critic Reinforcement Learning With Phased Actor (2024)0.00
• Reinforcement Learning With Adaptive Regularization For Safe Control Of Critical Systems (2024)0.00