行動前に選択せよ:連続制御のための空間的に分離された行動反復
Select before Act: Spatially Decoupled Action Repetition for Continuous Control
強化学習において、行動の各次元ごとに独立して「行動するか反復するか」を閉ループで選択する新フレームワークSDARを提案し、行動の持続性と多様性のバランスを改善した。
著者: Buqing Nie, Yangqing Fu, Yue Gao
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
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.
関連論文
- 構造的最大化可能なQ関数によるアクターフリー連続制御連続制御/強化学習
