mlsanityData to 14 Oct 2026

Select before Act: Spatially Decoupled Action Repetition for Continuous Control

arXiv 2502.06919 ↗First posted 10 Feb 2025cs.LG cs.AI cs.ROcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 46 references that are in the map. First posted on arXiv 10 Feb 2025.

Builds on

25 of 46 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Learning Uncertainty-Aware Temporally-Extended Actions8 Feb

Other references · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  7. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  8. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  9. 2016The Option-Critic Architecturecited by 448
  10. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
  11. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  12. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 260
12 more
  1. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 194
  2. 2021Hierarchical Reinforcement Learning By Discovering Intrinsic Optionscited by 58
  3. 2017Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learningcited by 39
  4. 2016Strategic Attentive Writer for Learning Macro-Actionscited by 30
  5. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
  6. 2021TempoRL: Learning When to Actcited by 25
  7. 2019The Termination Criticcited by 24
  8. 2021An Analysis of Frame-skipping in Reinforcement Learningcited by 18
  9. 2021TAAC: Temporally Abstract Actor-Critic for Continuous Controlcited by 15
  10. 2022Generative Planning for Temporally Coordinated Exploration in Reinforcement Learningcited by 10
  11. 2021Addressing Action Oscillations through Learning Policy Inertiacited by 9
  12. 2017Learning with Options that Terminate Off-Policycited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control
  2. 2024State-Novelty Guided Action Persistence in Deep Reinforcement Learning
  3. 2026Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning
  4. 2024Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
  5. 2026Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
  6. 2025Advancements and Challenges in Continual Reinforcement Learning: A Comprehensive Review
  7. 2025The Cell Must Go On: Agar.io for Continual Reinforcement Learning
  8. 2026Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning