Select before Act: Spatially Decoupled Action Repetition for Continuous Control
This work addresses the problem of action repetition in continuous control tasks for reinforcement learning researchers and practitioners, offering an incremental improvement over existing methods.
This work tackles the inflexibility of action repetition in reinforcement learning by proposing a novel framework called SDAR, which achieves improved sample efficiency and policy performance. SDAR outperforms existing repetition frameworks with higher policy performance and reduced action fluctuation.
Reinforcement Learning (RL) has achieved remarkable success in various continuous control tasks, such as robot manipulation and locomotion. Different to mainstream RL which makes decisions at individual steps, recent studies have incorporated action repetition into RL, achieving enhanced action persistence with improved sample efficiency and superior performance. However, existing methods treat all action dimensions as a whole during repetition, ignoring variations among them. This constraint leads to inflexibility in decisions, which reduces policy agility with inferior effectiveness. In this work, we propose a novel repetition framework called SDAR, which implements Spatially Decoupled Action Repetition through performing closed-loop act-or-repeat selection for each action dimension individually. SDAR achieves more flexible repetition strategies, leading to an improved balance between action persistence and diversity. Compared to existing repetition frameworks, SDAR is more sample efficient with higher policy performance and reduced action fluctuation. Experiments are conducted on various continuous control scenarios, demonstrating the effectiveness of spatially decoupled repetition design proposed in this work.