mlsanityData to 14 Oct 2026

Implicit Action Chunking for Smooth Continuous Control

arXiv 2605.19592 ↗First posted 19 May 2026cs.RO cs.AIcited by 0

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

Abstract (arXiv)

Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deployment. Explicit action chunking addresses this by predicting fixed-horizon trajectories but scales the policy output dimension proportionally with the horizon length, leading to optimization difficulties and incompatibility with standard step-wise interaction. To overcome these challenges, this paper proposes Dual-Window Smoothing (DWS), an implicit action chunking framework for smooth continuous control. Unlike explicit methods, DWS enforces temporal coherence without expanding the action space. It uses a dual-window design: an execution window that ensures physical smoothness through deterministic modulation, and a value window that aligns temporal-difference targets over the horizon to correct critic bias caused by open-loop execution. DWS also includes a lightweight actor-side temporal regularizer based on first-order action differences to promote global continuity. This design effectively bridges the gap between temporal abstraction and reactive step-wise control. Experiments on benchmarks including the DeepMind Control Suite and industrial energy management tasks show that DWS outperforms state-of-the-art (SOTA) baselines. In complex vision-based autonomous driving tasks, DWS achieves smoother control, safer behavior with reduced jitter, and attains a 100% success rate.

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 12 of its 36 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

12 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Reinforcement Learning with Action Chunking10 Jul

Other references · 11

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2018DeepMind Control Suitecited by 956
  4. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  5. 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
  6. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 169
  7. 2025Training-Time Action Conditioning for Efficient Real-Time Chunkingcited by 64
  8. 2020Regularizing Action Policies for Smooth Control with Reinforcement Learningcited by 59
  9. 2022L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learningcited by 27
  10. 2025Decoupled Q-Chunkingcited by 20
  11. 2025Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Rewardcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States
  2. 2026Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning
  3. 2026Action Chunking Proximal Policy Optimization with Feedback Correction
  4. 2025CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning
  5. 2026SmoothVLA: Aligning Vision-Language-Action Models with Physical Constraints via Intrinsic Smoothness Optimization
  6. 2026ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning
  7. 2026SEAM: Smooth Execution of Action-Chunked Motion for Vision-Language-Action Policies
  8. 2026Dynamic Execution Horizon Prediction for Chunk-based Robot Policies